Paper Citation Record · LEDGER

Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 22 inbound Pith citation observations for arXiv:2410.06981.

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

pith.paper-citation-record.v1
2410.06981 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 22 of 22 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:44:42.785494Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

1
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 70983da0-1086-49b3-831e-33292b241dce · inbound

Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models cites this paper.

Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 2009

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:42.785494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2bfe8af-0f1a-428d-8a4f-94873e1cd41d · inbound

Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks cites this paper.

Tensorization is a powerful but underexplored tool for compression and interpretability of neural networks Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T14:01:58.499011Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5976de11-95bb-44e3-859e-f70e38f5db6c · inbound

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models cites this paper.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:10.417992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86cee92f-a1b9-431d-8877-bfe84125fa91 · inbound

Sparse Autoencoders, Again? cites this paper.

Sparse Autoencoders, Again? Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T10:42:57.463947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46b16aba-c31e-47e2-8109-3c704d83b256 · inbound

Cross-Layer Discrete Concept Discovery for Interpreting Language Models cites this paper.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.980730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b13a9366-5b20-4c26-9cd0-b59e55016998 · inbound

On the transferability of Sparse Autoencoders for interpreting compressed models cites this paper.

On the transferability of Sparse Autoencoders for interpreting compressed models Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T15:24:45.749482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce8e6707-d6f6-424d-b6b4-2f8ffd3aea0e · inbound

Semantic Convergence: Investigating Shared Representations Across Scaled LLMs cites this paper.

Semantic Convergence: Investigating Shared Representations Across Scaled LLMs Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T15:39:46.530487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef32c3d8-9c2d-4bb4-8703-bb5d8b70c44a · inbound

Large Language Models Show Signs of Alignment with Human Neurocognition During Abstract Reasoning cites this paper.

Large Language Models Show Signs of Alignment with Human Neurocognition During Abstract Reasoning Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T21:10:32.008604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0702b72c-a1bd-4e7f-8bff-6e7e8eaa4cd0 · inbound

Toward Preference-aligned Large Language Models via Residual-based Model Steering cites this paper.

Toward Preference-aligned Large Language Models via Residual-based Model Steering Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:15.444750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 642e1732-bf3a-4522-bbdd-1e601a1434ab · inbound

Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation cites this paper.

Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 120

Resolution: unresolved; no resolver link, observed 2026-08-04T07:44:23.246746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fff88075-7530-4532-82b3-d520bb111bda · inbound

Understanding the Mechanism of Altruism in Large Language Models cites this paper.

Understanding the Mechanism of Altruism in Large Language Models Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 243

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T13:31:02.100837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2574460f-c7b1-435d-af9a-98b31dd91ced · inbound

Do Hallucination Neurons Generalize? Evidence from Cross-Domain Transfer in LLMs cites this paper.

Do Hallucination Neurons Generalize? Evidence from Cross-Domain Transfer in LLMs Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-15T00:48:25.099782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6fb46cb9-73dc-4bc8-b9ff-ac7d6e3b2b0e · inbound

Concepts Whisper While Syntax Shouts: Spectral Anti-Concentration and the Dual Geometry of Transformer Representations cites this paper.

Concepts Whisper While Syntax Shouts: Spectral Anti-Concentration and the Dual Geometry of Transformer Representations Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T16:51:08.342970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b846f23c-ce95-41d5-a7c8-f3bddcebd0ae · inbound

Rigorous Interpretation Is a Form of Evaluation cites this paper.

Rigorous Interpretation Is a Form of Evaluation Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 118

Resolution: verified exact; arxiv_id, observed 2026-05-08T21:09:11.880694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 64fcdb1a-cc49-487c-b44d-dbb1a32a2253 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 80

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:59:28.733478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation daf711f3-593b-49d3-8517-41eee2043f2f · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 80

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T04:59:45.078614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d1d4490d-2d8d-4daa-b5e6-9d31bf8920d5 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 80

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T21:53:47.180928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 98cb6fe1-22e4-4961-8a62-1e6d5abd3c4f · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T07:49:50.209649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 015403d3-8eb0-4f5e-a8d1-7fbacc01dcf9 · inbound

Structure Retention in Embedding Spaces as a Predictor of Benchmark Performance cites this paper.

Structure Retention in Embedding Spaces as a Predictor of Benchmark Performance Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 102

Resolution: verified exact; arxiv_id, observed 2026-05-22T06:24:40.841953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4827c50c-5f53-4875-b065-65b42c56f598 · inbound

Polymorphism Is Rotation: Operational Mechanistic Interpretability from a Two-Layer Transformer to Pythia-70m cites this paper.

Polymorphism Is Rotation: Operational Mechanistic Interpretability from a Two-Layer Transformer to Pythia-70m Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-06-30T14:14:45.507202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fd691377-0539-4f4d-bcde-e36749a74aac · inbound

Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects cites this paper.

Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T10:03:56.411662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cabc821-550e-47e1-8622-00290884218a · inbound

What, Where, and How: Disentangling the Roles of Task, Language, and Model in Code Model Representations cites this paper.

What, Where, and How: Disentangling the Roles of Task, Language, and Model in Code Model Representations Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T07:20:35.895944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.