Paper Citation Record · LEDGER

Individual Parameters in Weight-Sparse Transformers Appear Interpretable

As of 20 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 0 inbound Pith citation observations for arXiv:2607.02964.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2607.02964 v1

Coverage vector

measured 17 of 17 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-12T05:48:11.148130Z

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

17 of 17 outbound references displayed

verified exact0
verified fuzzy0
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation be8bee61-c3f9-4374-b900-fbd07da20073 · outbound

This paper cites Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition.

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 9ca8ea7a-716c-4ebb-827f-b60ab0223303 · outbound

This paper cites Stochastic Parameter Decomposition.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable Stochastic Parameter Decomposition

Reference 2

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 ca04b810-6100-482b-becf-51aca6298bf3 · outbound

This paper cites Identifying Sparsely Active Circuits Through Local Loss Landscape Decomposition.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable Identifying Sparsely Active Circuits Through Local Loss Landscape Decomposition

Reference 3

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 351b3ec3-765a-436a-bc08-2402e5152992 · outbound

This paper cites Toy Models of Superposition.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable Toy Models of Superposition

Reference 4

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 a6e148a5-4c3f-41b5-8eb1-ab5eb592b37e · outbound

This paper cites The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

Reference 5

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 47d93ea2-0620-425d-9637-1a37e52568bb · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 6

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 d6d1a929-4735-4620-a586-de5cd06c02a0 · outbound

This paper cites V ., Baker, B., and Mossing, D.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable V ., Baker, B., and Mossing, D

Reference 7

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 82de02b5-f4c0-4f02-972a-06cae982d7ee · outbound

This paper cites Finding Neurons in a Haystack: Case Studies with Sparse Probing.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable Finding Neurons in a Haystack: Case Studies with Sparse Probing

Reference 8

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 8a0b6202-1977-4f87-88fc-b2b6c390d8c5 · outbound

This paper cites In-context Learning and Induction Heads.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable In-context Learning and Induction Heads

Reference 9

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 3303a764-5acc-4ddd-b355-a07c2a985c6d · outbound

This paper cites Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types

Reference 10

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 188d04fa-fe76-42a9-bfe9-5b0a320efc01 · outbound

This paper cites Bilinear MLPs enable weight-based mechanistic interpretability.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable Bilinear MLPs enable weight-based mechanistic interpretability

Reference 11

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 83ec2fbe-634d-46f9-835e-e2c7cdc267d8 · outbound

This paper cites Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 12

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 6446af1c-2452-4c35-bf17-88c0dcc3cbd2 · outbound

This paper cites The Super Weight in Large Language Models.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable The Super Weight in Large Language Models

Reference 13

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 1679fa88-3a3b-4be3-b192-9fe9a3727f10 · outbound

This paper cites (2025) model, which is not publicly released, and stream The Pile (Gao et al.,.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable (2025) model, which is not publicly released, and stream The Pile (Gao et al.,

Reference 14

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 f8fde31a-bab4-4ad1-bf0f-2f1a07cfb6bb · outbound

This paper cites For the Drori (2026) sparse and dense models we use SimpleStories (Drori, 2026), which is the actual training corpus.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable For the Drori (2026) sparse and dense models we use SimpleStories (Drori, 2026), which is the actual training corpus

Reference 15

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 04b97879-9a3d-4926-9669-04e9d75470d4 · outbound

This paper cites not interpretable,.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable not interpretable,

Reference 16

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 0f7a0b3d-800c-49c2-a082-72cf250172d0 · outbound

This paper cites speech-verb detector.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable speech-verb detector

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-12T05:48:11.148130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.