Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-10T14:55:02.296395Z
Paper Citation Record · LEDGER
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
As of 14 August 2026, this Paper Citation Record lists 98 of 98 outbound references and 14 inbound Pith citation observations for arXiv:2501.14926.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-06T22:48:35.756321Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-01T13:45:45.794455Z
Reference resolution
98 of 98 outbound references displayed
- verified exact7
- verified fuzzy21
- unresolved70
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 09b1940d-c108-4a28-8004-fa2c71e34720 · outbound
This paper cites Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, and Simon Lacoste-Julien.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, and Simon Lacoste-Julien
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.928897Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5ff0f2e1-5552-4681-9d87-e8bca6b4e05e · outbound
This paper cites Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.933680Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1343e9ed-b73c-47b6-9cb1-6bd36fea3079 · outbound
This paper cites Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.937875Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 617b012a-0737-4cfb-a035-3ad389d2c153 · outbound
This paper cites Towards monosemanticity: Decomposing language models with dictionary learning.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Towards monosemanticity: Decomposing language models with dictionary learning
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.941999Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 17a24b05-cdfe-45f0-a115-ef6429f162a1 · outbound
This paper cites Circuits in superposition: Compressing many small neural networks into one, Oct 2024.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Circuits in superposition: Compressing many small neural networks into one, Oct 2024
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.945578Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 193ed564-f8a4-4aad-a858-f59e4a85b671 · outbound
This paper cites Showing sae latents are not atomic using meta-saes, Aug 2024.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Showing sae latents are not atomic using meta-saes, Aug 2024
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.949426Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d30465e6-3b9d-4f7b-bb16-4213df4a7c54 · outbound
This paper cites BatchTopK Sparse Autoencoders.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition BatchTopK Sparse Autoencoders
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.953347Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f9a57fa0-9dce-4478-bfd3-d50e6ce8a2f3 · outbound
This paper cites Curve detectors.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Curve detectors
Reference 8
- Resolution
- verified exact
- doi, observed 2026-08-10T14:55:02.364185Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 5a849cf2-d68c-421a-8e7a-34e97ad9fceb · outbound
This paper cites Sparse Interventions in Language Models with Differentiable Masking.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Sparse Interventions in Language Models with Differentiable Masking
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-08-10T14:55:03.051866Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 6219a49f-4d1d-40ad-a3ae-772fa3017154 · outbound
This paper cites Low-Complexity Probing via Finding Subnetworks.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Low-Complexity Probing via Finding Subnetworks
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.964739Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dc2834c1-68c5-4f5a-ac30-c087d3e5389c · outbound
This paper cites Scaling sparse feature circuit finding to gemma 9b, Jan 2025.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Scaling sparse feature circuit finding to gemma 9b, Jan 2025
Reference 11
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.968431Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1f48ec39-8b39-4b38-a953-a1d9e47a4db5 · outbound
This paper cites Causal scrubbing: a method for rigorously testing interpretability hypotheses [redwood research], December 2022.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Causal scrubbing: a method for rigorously testing interpretability hypotheses [redwood research], December 2022
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.971790Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 546cff5e-8947-47fd-934a-e30a42636ba2 · outbound
This paper cites A is for absorption: Studying feature splitting and absorption in sparse autoencoders, 2024.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition A is for absorption: Studying feature splitting and absorption in sparse autoencoders, 2024
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.975190Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 04522526-8efe-485b-a520-813d8c30e6cf · outbound
This paper cites Mechanistic anomaly detection and elk, 11 2022.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Mechanistic anomaly detection and elk, 11 2022
Reference 14
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.978532Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 33eb7777-8d0c-402d-97e8-cc2dcb5d71a1 · outbound
This paper cites Churchland and Krishna V.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Churchland and Krishna V
Reference 15
- Resolution
- verified exact
- raw_fallback, observed 2026-08-10T14:55:02.961740Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 9db26d29-d035-4ea8-beff-77c8a4529424 · outbound
This paper cites Towards automated circuit discovery for mechanistic interpretability.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Towards automated circuit discovery for mechanistic interpretability
Reference 16
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.985118Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6b099cc3-2232-4000-819f-47c3cd3e1f91 · outbound
This paper cites Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.988432Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 38b58961-102f-43bd-a77d-cbb852b1bd9d · outbound
This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Sparse Autoencoders Find Highly Interpretable Features in Language Models
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.992243Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a9b78691-305a-4fe5-8d84-79138553c88c · outbound
This paper cites Analyzing Transformers in Embedding Space.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Analyzing Transformers in Embedding Space
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.995894Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 02b195aa-5c63-464e-a5f2-1017fd31ba0a · outbound
This paper cites Attention is not all you need: Pure attention loses rank doubly exponentially with depth, 2023.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Attention is not all you need: Pure attention loses rank doubly exponentially with depth, 2023
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:01.999413Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 857d6d2a-c940-435b-af91-f7e7e6bbd5e5 · outbound
This paper cites Transcoders Find Interpretable LLM Feature Circuits.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Transcoders Find Interpretable LLM Feature Circuits
Reference 21
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.002736Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 880d3fbb-f6e2-47a6-ae83-63e9266f9aa4 · outbound
This paper cites Toy models of superposition, 2022.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Toy models of superposition, 2022
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.006464Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5874e8a3-6850-4b3d-b82f-6b03d75d2222 · outbound
This paper cites Not All Language Model Features Are One-Dimensionally Linear.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Not All Language Model Features Are One-Dimensionally Linear
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.009949Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 012ba044-59ae-4167-98ad-600cc8c965b8 · outbound
This paper cites Decomposing The Dark Matter of Sparse Autoencoders.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Decomposing The Dark Matter of Sparse Autoencoders
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.013757Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6dff0965-55a0-415e-8a6d-9902d668811e · outbound
This paper cites A Review of Sparse Expert Models in Deep Learning.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition A Review of Sparse Expert Models in Deep Learning
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.018437Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fecae163-1a60-4bcd-9a43-0c868c0a2d76 · outbound
This paper cites Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.022650Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fe569175-70a4-4fd3-a0d0-eadd57c48af5 · outbound
This paper cites Scaling and evaluating sparse autoencoders.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Scaling and evaluating sparse autoencoders
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.026867Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 024c1d07-87f5-4b2e-9bc5-4ecb81d25b8b · outbound
This paper cites Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.030913Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 07062fd1-bf6e-49ed-897f-9cf7533316fa · outbound
This paper cites A novel variational form of the Schatten-$p$ quasi-norm.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition A novel variational form of the Schatten-$p$ quasi-norm
Reference 29
- Resolution
- verified exact
- local_arxiv, observed 2026-08-10T14:55:02.770315Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 62522e02-b85a-4cec-a10e-70bf871d2e0d · outbound
This paper cites Compact Proofs of Model Performance via Mechanistic Interpretability.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Compact Proofs of Model Performance via Mechanistic Interpretability
Reference 30
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.039261Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 59b15c4c-8ebb-45b7-b18a-d67fc4e75293 · outbound
This paper cites Superposition, memorization, and double descent, Jan 2023.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Superposition, memorization, and double descent, Jan 2023
Reference 31
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.043051Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 31d22bdb-6423-4d7c-b551-c7576b6efdd1 · outbound
This paper cites an unresolved cited work.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Unresolved cited work
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.046632Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7b68efe4-0b30-496b-92a4-11f81b2f98d3 · outbound
This paper cites Mathematical Models of Computation in Superposition.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Mathematical Models of Computation in Superposition
Reference 33
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.050076Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 03117473-def8-40a7-9cfa-f4d34cc3d4ac · outbound
This paper cites Jacobs, Michael I.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Jacobs, Michael I
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.054098Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 87c78947-4ce7-4a4e-aea2-2cd111d9b2f7 · outbound
This paper cites Polysemantic attention head in a 4-layer transformer, Nov 2023.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Polysemantic attention head in a 4-layer transformer, Nov 2023
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.057917Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5a127bcf-b2bc-4b05-9636-1238ef28e54a · outbound
This paper cites Attention head superposition, May 2023.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Attention head superposition, May 2023
Reference 36
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.061574Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a8f4edbc-d8a3-4648-be3c-0f7950c0ea0a · outbound
This paper cites Tanh penalty in dictionary learning.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Tanh penalty in dictionary learning
Reference 37
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.065337Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 000081ae-18c9-4598-aaeb-77de74c9ecdc · outbound
This paper cites Kingma and Jimmy Ba.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Kingma and Jimmy Ba
Reference 38
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.069060Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 87a9e57e-b220-48c7-8bb7-ef920ac1b907 · outbound
This paper cites Knechtli, M.
Reference 39
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.072574Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4dc3b048-ff07-46d0-b532-91eb721ae6a2 · outbound
This paper cites AtP*: An efficient and scalable method for localizing LLM behaviour to components.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition AtP*: An efficient and scalable method for localizing LLM behaviour to components
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.076326Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ad53358e-91d1-4a49-817a-606c6c58cb78 · outbound
This paper cites Optimal brain damage.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Optimal brain damage
Reference 41
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.080342Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e0ea3d51-4641-423a-9319-c04bd492970c · outbound
This paper cites Sparse deep belief net model for visual area v2.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Sparse deep belief net model for visual area v2
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.387622Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 9de2a273-ae2e-4abd-81fe-c361c33ac11e · outbound
This paper cites Break It Down: Evidence for Structural Compositionality in Neural Networks.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Break It Down: Evidence for Structural Compositionality in Neural Networks
Reference 43
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.087913Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9bad77fd-1515-470f-9938-01db5c3824ca · outbound
This paper cites Measuring the intrinsic dimension of objective landscapes, 2018.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Measuring the intrinsic dimension of objective landscapes, 2018
Reference 44
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.091682Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 58ffde52-cb39-4fcc-916f-b7a6e57402ae · outbound
This paper cites Convergent Learning: Do different neural networks learn the same representations?.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Convergent Learning: Do different neural networks learn the same representations?
Reference 45
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.095279Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 46e32e6c-8df0-499c-8b32-7ac1d82b37a8 · outbound
This paper cites Sparse crosscoders for cross-layer features and model diffing, October 2024.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Sparse crosscoders for cross-layer features and model diffing, October 2024
Reference 46
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.099277Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 845b9c97-f3d6-4de5-8330-3c630df2878b · outbound
This paper cites Decoupled Weight Decay Regularization.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Decoupled Weight Decay Regularization
Reference 47
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.102887Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 331cce98-8d87-40f7-aba9-ff24e5432c19 · outbound
This paper cites Towards principled evaluations of sparse autoencoders for interpretability and control.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Towards principled evaluations of sparse autoencoders for interpretability and control
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.364189Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation b5d8c57a-bd40-40cb-811f-fe9ad47dd6e4 · outbound
This paper cites k-Sparse Autoencoders.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition k-Sparse Autoencoders
Reference 49
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.110319Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6834a095-b374-4651-9123-b814e92f7d5a · outbound
This paper cites Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
Reference 50
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.114088Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b781cdef-b4b0-4eed-9b57-315f6e80de7b · outbound
This paper cites Gated attention blocks: Preliminary progress toward removing attention head superposition.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Gated attention blocks: Preliminary progress toward removing attention head superposition
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.352088Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 5fe6a4c4-e882-495b-8f9c-af03bdb5133f · outbound
This paper cites McClelland and David E.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition McClelland and David E
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.340242Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 03a23172-c94a-442f-a85a-7d6577c07f17 · outbound
This paper cites Singular value representation: A new graph perspective on neural networks.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Singular value representation: A new graph perspective on neural networks
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.329072Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation a07837f8-5e87-479d-81a6-64996ac5fe4c · outbound
This paper cites Sae feature geometry is outside the superposition hypothesis, Sep 2024.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Sae feature geometry is outside the superposition hypothesis, Sep 2024
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.317228Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 6287fb88-e5a9-49a1-aa80-5aa1a46dd0bf · outbound
This paper cites Locating and editing factual associations in gpt, 2023 a.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Locating and editing factual associations in gpt, 2023 a
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.306178Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation c52c97b4-67f4-4fea-8c0c-5bfc2ca0d538 · outbound
This paper cites Mass-Editing Memory in a Transformer.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Mass-Editing Memory in a Transformer
Reference 56
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.135872Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fadf4aad-8399-4619-8291-20941ad88368 · outbound
This paper cites The Quantization Model of Neural Scaling.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition The Quantization Model of Neural Scaling
Reference 57
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.139710Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8d7914cc-6360-4120-9e4a-3c8e1439aca2 · outbound
This paper cites The singular value decompositions of transformer weight matrices are highly interpretable, Nov 2022.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition The singular value decompositions of transformer weight matrices are highly interpretable, Nov 2022
Reference 58
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.295667Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation ec4abf73-5a8b-4fc7-8f81-55987805304e · outbound
This paper cites Pruning Convolutional Neural Networks for Resource Efficient Inference.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Pruning Convolutional Neural Networks for Resource Efficient Inference
Reference 59
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.147411Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e2919f8f-76c8-4477-8c12-77ceb7f69939 · outbound
This paper cites Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Circuit Compositions: Exploring Modular Structures in Transformer-Based Language Models
Reference 60
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.151456Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 27b7520c-61e7-4772-bfb8-c3d9745786c0 · outbound
This paper cites On the importance of single directions for generalization.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition On the importance of single directions for generalization
Reference 61
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.155256Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 49ed94da-e321-4735-84ce-ce96e7d4d2e5 · outbound
This paper cites Skeletonization: A technique for trimming the fat from a network via relevance assessment.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Skeletonization: A technique for trimming the fat from a network via relevance assessment
Reference 62
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.159103Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b98f766f-a2fc-4676-98d8-aeb67bbfcfa1 · outbound
This paper cites Attribution patching: Activation patching at industrial scale.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Attribution patching: Activation patching at industrial scale
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.276701Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 1374f3d1-bc6d-48ac-b5ac-7f66034b2934 · outbound
This paper cites Attribution patching: Activation patching at industrial scale.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Attribution patching: Activation patching at industrial scale
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.264069Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 08ade89d-594f-4317-a75f-d3b6ec60a05c · outbound
This paper cites Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
Reference 65
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.169387Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 92a4349c-eb65-456d-800c-8d576feb9b08 · outbound
This paper cites interpreting gpt: the logit lens, August 2020.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition interpreting gpt: the logit lens, August 2020
Reference 66
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.252185Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation dc7767ef-0762-4056-bc71-29acaebb861d · outbound
This paper cites Weight superposition, May 2023.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Weight superposition, May 2023
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.239294Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 3cc897ff-fb3e-4020-826a-5a91854da724 · outbound
This paper cites The next five hurdles, July 2024 a.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition The next five hurdles, July 2024 a
Reference 68
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.227224Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 6b1383cf-8fec-4f0a-b5e9-0645cc86932a · outbound
This paper cites What is a linear representation? what is a multidimensional feature?, July 2024 b.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition What is a linear representation? what is a multidimensional feature?, July 2024 b
Reference 69
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.216649Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 49546271-21b0-4089-b05c-35f015aa3fda · outbound
This paper cites An overview of early vision in inceptionv1.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition An overview of early vision in inceptionv1
Reference 70
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.190525Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 243994dc-b4c8-4faf-afb4-ee8edacceb51 · outbound
This paper cites Zoom in: An introduction to circuits.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Zoom in: An introduction to circuits
Reference 71
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.205141Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation e3e18910-6f01-4337-ad66-3b0d06010f01 · outbound
This paper cites Monet: Mixture of Monosemantic Experts for Transformers.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Monet: Mixture of Monosemantic Experts for Transformers
Reference 72
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.197434Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 910a6b16-b162-447d-bd62-2bfe8d388ef1 · outbound
This paper cites Neural Sculpting: Uncovering hierarchically modular task structure in neural networks through pruning and network analysis.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Neural Sculpting: Uncovering hierarchically modular task structure in neural networks through pruning and network analysis
Reference 73
- Resolution
- verified exact
- local_arxiv, observed 2026-08-10T14:55:02.481775Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 819e658e-e88e-4ba8-a14c-e9a8c1919376 · outbound
This paper cites Weight-based Decomposition: A Case for Bilinear MLPs.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Weight-based Decomposition: A Case for Bilinear MLPs
Reference 74
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.205020Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation aac334ca-267f-478c-a708-e23b1d51c23f · outbound
This paper cites Bilinear MLPs enable weight-based mechanistic interpretability.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Bilinear MLPs enable weight-based mechanistic interpretability
Reference 75
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.209060Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2dcc5a60-cc86-4dcf-ad3c-2bf4592674d1 · outbound
This paper cites Weight banding.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Weight banding
Reference 76
- Resolution
- verified exact
- doi, observed 2026-08-10T14:55:02.339107Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation a07a3579-6e7d-4cd3-af3f-134c2ec52a07 · outbound
This paper cites Explanatory Masks for Neural Network Interpretability.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Explanatory Masks for Neural Network Interpretability
Reference 77
- Resolution
- verified exact
- local_arxiv, observed 2026-08-10T14:55:02.447075Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation c023110c-7bee-4db3-87b1-4e64957811c6 · outbound
This paper cites Rumelhart, Geoffrey E.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Rumelhart, Geoffrey E
Reference 78
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.193658Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation f161cfbf-a8a4-484f-b798-e2f72d98a296 · outbound
This paper cites Sparsify: A mechanistic interpretability research agenda, April 2024.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Sparsify: A mechanistic interpretability research agenda, April 2024
Reference 79
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.182804Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 54f09e4d-853f-4c21-b5b3-fe2dba7a60ed · outbound
This paper cites Taking features out of superposition with sparse autoencoders, Dec 2022.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Taking features out of superposition with sparse autoencoders, Dec 2022
Reference 80
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.229021Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5d1fdc47-bc03-46b5-b430-4f90cb9c1ea1 · outbound
This paper cites Open Problems in Mechanistic Interpretability.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Open Problems in Mechanistic Interpretability
Reference 81
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.232925Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation acf6724a-f502-4933-9f6b-c2fe1490364d · outbound
This paper cites Dropout: A simple way to prevent neural networks from overfitting.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Dropout: A simple way to prevent neural networks from overfitting
Reference 82
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.237281Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1a166d52-8cc1-4aed-bea8-89c523f8bfd9 · outbound
This paper cites Axiomatic attribution for deep networks, 2017.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Axiomatic attribution for deep networks, 2017
Reference 83
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.240996Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 365fa9a5-2ec5-48e9-9c2b-8f25d1773552 · outbound
This paper cites Attribution Patching Outperforms Automated Circuit Discovery.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Attribution Patching Outperforms Automated Circuit Discovery
Reference 84
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.244675Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 913a9a47-88bf-4854-96a8-981f6f9d8455 · outbound
This paper cites true features.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition true features
Reference 85
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.248489Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f8a613b4-c457-4b60-bd29-20ce2b407a8b · outbound
This paper cites Toward a mathematical framework for computation in superposition, Jan 2024.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Toward a mathematical framework for computation in superposition, Jan 2024
Reference 86
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.147118Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 2a14ff0d-55de-4ad8-ac87-3dcbb03fbbc5 · outbound
This paper cites Residual networks behave like ensembles of relatively shallow networks, 2016.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Residual networks behave like ensembles of relatively shallow networks, 2016
Reference 87
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.135959Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 53b277d9-50c4-4f17-b84a-ae32a49855cd · outbound
This paper cites Causal mediation analysis for interpreting neural nlp: The case of gender bias, 2020.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Causal mediation analysis for interpreting neural nlp: The case of gender bias, 2020
Reference 88
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.259446Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1c87052b-bbff-461b-857f-87f917c4e241 · outbound
This paper cites Visualizing weights.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Visualizing weights
Reference 89
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.262889Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bc79648e-9b45-462e-8880-808f654d0a90 · outbound
This paper cites Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient
Reference 90
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.266549Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation afab162a-b487-4298-9b9a-441122dd8fd5 · outbound
This paper cites Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
Reference 91
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.270268Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c67c9982-effc-4715-8cba-4de6553e2ed8 · outbound
This paper cites Algebraic geometry and statistical learning theory, volume 25.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Algebraic geometry and statistical learning theory, volume 25
Reference 92
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.273821Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5032a9a4-3397-4454-8d39-f6bf04781513 · outbound
This paper cites Addressing feature suppression in saes, Feb 2024.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Addressing feature suppression in saes, Feb 2024
Reference 93
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.277248Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f0b4bf34-7058-46f3-8ec0-6e6889796caa · outbound
This paper cites Decomposing the qk circuit with bilinear sparse dictionary learning, July 2024.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Decomposing the qk circuit with bilinear sparse dictionary learning, July 2024
Reference 94
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.104946Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 07644e3b-7f55-436e-bf61-ead212f82cc6 · outbound
This paper cites Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors
Reference 95
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.284507Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0d66d4f7-5417-49f3-be64-af18a795f56b · outbound
This paper cites Understanding deep learning requires rethinking generalization.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Understanding deep learning requires rethinking generalization
Reference 96
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.288353Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7ab53c8e-0d78-4977-bd66-0b10c97c2998 · outbound
This paper cites Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?
Reference 97
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T14:55:02.292272Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 66863b85-3a43-49a3-8e0e-ee70125fd2b6 · outbound
This paper cites Moefication: Transformer feed-forward layers are mixtures of experts, 2022.
Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Moefication: Transformer feed-forward layers are mixtures of experts, 2022
Reference 98
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-10T14:55:03.094226Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Pith citing papers
Observation 949792ff-a09c-423b-af8d-70de132f16cb · inbound
Stochastic Parameter Decomposition cites this paper.
Stochastic Parameter Decomposition Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T22:48:35.756321Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9ba45641-6e74-4ebd-b363-e38974e2b928 · inbound
Compressed Computation: Dense Circuits in a Toy Model of the Universal-AND Problem cites this paper.
Compressed Computation: Dense Circuits in a Toy Model of the Universal-AND Problem Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Reference 3
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T17:53:54.937410Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation faf94b8e-5da5-4fb6-b848-1c0faa36b836 · inbound
Distribution-Aware Feature Selection for SAEs cites this paper.
Distribution-Aware Feature Selection for SAEs Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Reference 2009
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T14:27:25.414379Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 970d5072-366b-40f5-822d-c524a60c0c1e · inbound
Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks cites this paper.
Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Reference 7
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-18T18:26:43.729817Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 97c1011c-aafe-420a-98b0-3c93a5cfaa63 · inbound
From Mechanistic to Compositional Interpretability cites this paper.
From Mechanistic to Compositional Interpretability Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Reference 165
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T07:31:25.724304Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation d4ce204f-df02-4e4e-905c-993e9ec9ba84 · inbound
From Mechanistic to Compositional Interpretability cites this paper.
From Mechanistic to Compositional Interpretability Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Reference 11
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-01T13:45:45.796059Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 0db6320c-f8c7-465e-814b-e2be99bfdfde · inbound
WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.
WriteSAE: Sparse Autoencoders for Recurrent State Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Reference 96
- Resolution
- verified exact
- arxiv_id, observed 2026-05-14T20:59:28.694229Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 301edd04-c892-43ea-9e67-1927f76d2a69 · inbound
WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.
WriteSAE: Sparse Autoencoders for Recurrent State Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Reference 96
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T04:59:45.129312Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 1fdbf09e-296c-4b81-87df-b3ffdcc8d030 · inbound
WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.
WriteSAE: Sparse Autoencoders for Recurrent State Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Reference 96
- Resolution
- verified exact
- arxiv_id, observed 2026-05-20T21:53:47.229223Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation 7ef79c78-70c0-401c-bf1c-8af855b4db2d · inbound
WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.
WriteSAE: Sparse Autoencoders for Recurrent State Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-05-21T07:49:50.131311Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.
Observation be8bee61-c3f9-4374-b900-fbd07da20073 · inbound
Individual Parameters in Weight-Sparse Transformers Appear Interpretable cites this paper.
Individual Parameters in Weight-Sparse Transformers Appear Interpretable Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Reference 1
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T05:48:11.148130Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d27582ca-8c0b-4f9a-b194-fd0664b6eb63 · inbound
Compressed Computation under $L^4$ Loss is likely Computation in Superposition cites this paper.
Compressed Computation under $L^4$ Loss is likely Computation in Superposition Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-07-11T13:19:28.945702Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8e665692-cb8f-4e65-a9a0-5204335db1d1 · inbound
Targeted Recovery of Weight-Space Mechanisms From Neural Networks cites this paper.
Targeted Recovery of Weight-Space Mechanisms From Neural Networks Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Reference 32
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T10:39:49.368052Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1a523d31-c07d-4b39-8f31-8764ba993132 · inbound
Targeted Recovery of Weight-Space Mechanisms From Neural Networks cites this paper.
Targeted Recovery of Weight-Space Mechanisms From Neural Networks Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Reference 150
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T10:40:00.727345Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.