Paper Citation Record · LEDGER

Automatically Interpreting Millions of Features in Large Language Models

As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 45 inbound Pith citation observations for arXiv:2410.13928.

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

pith.paper-citation-record.v1
2410.13928 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 45 of 45 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T23:21:24.356298Z

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

2
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 93ba4555-f892-4879-b9d5-5d231f5d255a · inbound

Interpretable Company Similarity with Sparse Autoencoders cites this paper.

Interpretable Company Similarity with Sparse Autoencoders Automatically Interpreting Millions of Features in Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T23:21:24.356298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf2712e3-c2a5-4c81-826a-ad5abe3ff685 · inbound

Interpretable Steering of Large Language Models with Feature Guided Activation Additions cites this paper.

Interpretable Steering of Large Language Models with Feature Guided Activation Additions Automatically Interpreting Millions of Features in Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T19:34:26.933320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 490207d3-85f9-47f7-8811-19206fda2a07 · inbound

Propositional Interpretability in Artificial Intelligence cites this paper.

Propositional Interpretability in Artificial Intelligence Automatically Interpreting Millions of Features in Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T14:02:12.790737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b5e109b-dc60-434f-b6d1-9e38a1c46758 · inbound

Sparse Autoencoders Trained on the Same Data Learn Different Features cites this paper.

Sparse Autoencoders Trained on the Same Data Learn Different Features Automatically Interpreting Millions of Features in Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T11:58:37.143219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3ae2cc8-7ddf-476a-8d9e-5e36b9d259a3 · inbound

SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders cites this paper.

SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders Automatically Interpreting Millions of Features in Large Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-10T01:04:57.206452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d3227a6-362c-4f27-9081-ab790f79be4d · inbound

Transcoders Beat Sparse Autoencoders for Interpretability cites this paper.

Transcoders Beat Sparse Autoencoders for Interpretability Automatically Interpreting Millions of Features in Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.884852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1a4bfb8-1bce-41ae-bf01-96cc4d3259b4 · inbound

Partially Rewriting a Transformer in Natural Language cites this paper.

Partially Rewriting a Transformer in Natural Language Automatically Interpreting Millions of Features in Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T22:21:50.763556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7018977c-9838-49b4-badc-ba1620c36b4b · inbound

Converting MLPs into Polynomials in Closed Form cites this paper.

Converting MLPs into Polynomials in Closed Form Automatically Interpreting Millions of Features in Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T16:58:44.732303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 404a1caf-9e0e-48b1-b0bc-f3deb3b9ee22 · inbound

Breaking Down Bias: On The Limits of Generalizable Pruning Strategies cites this paper.

Breaking Down Bias: On The Limits of Generalizable Pruning Strategies Automatically Interpreting Millions of Features in Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-08T11:42:07.609217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec0bdb8c-202d-4452-97e6-e8969bf8b555 · 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 Automatically Interpreting Millions of Features in Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:43.094342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 69d5d226-67de-45f7-aa85-cd7999a7ea30 · inbound

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs cites this paper.

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs Automatically Interpreting Millions of Features in Large Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:02.798784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dced67a-930b-4899-906d-9d518eb3e32c · inbound

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy cites this paper.

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy Automatically Interpreting Millions of Features in Large Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:26.125107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e6b6711-37ba-499f-b663-95b831dca041 · inbound

Evaluating SAE interpretability without explanations cites this paper.

Evaluating SAE interpretability without explanations Automatically Interpreting Millions of Features in Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:51.640958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3a332b2-4bc4-4fd7-a769-e59f5658fa1c · inbound

Insights into a radiology-specialised multimodal large language model with sparse autoencoders cites this paper.

Insights into a radiology-specialised multimodal large language model with sparse autoencoders Automatically Interpreting Millions of Features in Large Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T16:40:43.382708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc944e05-a04d-4239-905f-0ffb17c18ff6 · inbound

Teach Old SAEs New Domain Tricks with Boosting cites this paper.

Teach Old SAEs New Domain Tricks with Boosting Automatically Interpreting Millions of Features in Large Language Models

Reference 1997

Resolution: unresolved; no resolver link, observed 2026-08-06T16:40:29.278577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5a8fa38-3718-4b12-9db2-5754e64ce507 · inbound

Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders cites this paper.

Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders Automatically Interpreting Millions of Features in Large Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-06T11:01:42.861396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38cada16-d398-4e83-9f60-d806293f9950 · inbound

Distribution-Aware Feature Selection for SAEs cites this paper.

Distribution-Aware Feature Selection for SAEs Automatically Interpreting Millions of Features in Large Language Models

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-05T14:27:25.448907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51200a8a-a44b-4b9a-a1cf-f3c2243dc8dd · inbound

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework cites this paper.

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework Automatically Interpreting Millions of Features in Large Language Models

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-18T18:16:43.727392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8f99d151-6988-49f1-b0a0-644c1b031df4 · inbound

Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing Approach cites this paper.

Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing Approach Automatically Interpreting Millions of Features in Large Language Models

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-18T02:00:40.020715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 80cfe4ec-b4c5-455a-9f9b-ca5f4da4545e · inbound

Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing Approach cites this paper.

Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing Approach Automatically Interpreting Millions of Features in Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T00:23:29.455409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40fa6dbd-3e7a-44e4-9b18-20d62b4e15f5 · inbound

Prototype Transformer: Towards Language Model Architectures Interpretable by Design cites this paper.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Automatically Interpreting Millions of Features in Large Language Models

Reference 1995

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:44.908484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24ca6d44-11fb-4f92-bdf2-1bd1d35942ab · inbound

Visual Persuasion: What Influences Decisions of Vision-Language Models? cites this paper.

Visual Persuasion: What Influences Decisions of Vision-Language Models? Automatically Interpreting Millions of Features in Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T23:00:26.827244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0a86bbe-392a-4f0e-b54e-70c86ce35603 · inbound

CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs cites this paper.

CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs Automatically Interpreting Millions of Features in Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T17:47:09.249674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99504919-6994-4918-bf36-9c0050b1a81a · inbound

MetaSAEs: Joint Training with a Decomposability Penalty Produces More Atomic Sparse Autoencoder Latents cites this paper.

MetaSAEs: Joint Training with a Decomposability Penalty Produces More Atomic Sparse Autoencoder Latents Automatically Interpreting Millions of Features in Large Language Models

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:43:11.174235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 18442c76-67d5-4f2f-b0b5-2d67361ad47b · inbound

LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering cites this paper.

LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering Automatically Interpreting Millions of Features in Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T05:36:47.912974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68a18cc7-8459-40cc-9acb-5163d2c730bb · inbound

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs cites this paper.

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs Automatically Interpreting Millions of Features in Large Language Models

Reference 80

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:35:57.738845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e7e69111-eaf2-43e7-a12a-c31c0c074c66 · inbound

From Token Lists to Graph Motifs: Weisfeiler-Lehman Analysis of Sparse Autoencoder Features cites this paper.

From Token Lists to Graph Motifs: Weisfeiler-Lehman Analysis of Sparse Autoencoder Features Automatically Interpreting Millions of Features in Large Language Models

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:16:11.098765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c22a0357-cea8-4493-bb17-9119b92e3f35 · inbound

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders cites this paper.

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders Automatically Interpreting Millions of Features in Large Language Models

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:15:54.269344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9408900b-b8ff-4f83-aad1-f656f7fbcb0e · inbound

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders cites this paper.

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders Automatically Interpreting Millions of Features in Large Language Models

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-12T07:16:25.542255Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 92412ab3-e893-4d21-a272-7edffd59c421 · inbound

Domain Restriction via Multi SAE Layer Transitions cites this paper.

Domain Restriction via Multi SAE Layer Transitions Automatically Interpreting Millions of Features in Large Language Models

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T06:02:23.786790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5b619e30-0b39-4ad3-92ea-65ee8030c09b · inbound

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space cites this paper.

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space Automatically Interpreting Millions of Features in Large Language Models

Reference 168

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T05:27:19.296590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 90c19cd7-8b28-4b13-9d10-29df29899b30 · inbound

Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features cites this paper.

Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features Automatically Interpreting Millions of Features in Large Language Models

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-14T20:29:27.959279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2023cc4a-ebf5-4238-84e6-b6d728fb9fbd · inbound

Why Retrieval-Augmented Generation Fails: A Graph Perspective cites this paper.

Why Retrieval-Augmented Generation Fails: A Graph Perspective Automatically Interpreting Millions of Features in Large Language Models

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-15T04:49:44.307236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4472d2ca-8d2f-417b-ba76-a821d63b5696 · inbound

The Rate-Distortion-Polysemanticity Tradeoff in SAEs cites this paper.

The Rate-Distortion-Polysemanticity Tradeoff in SAEs Automatically Interpreting Millions of Features in Large Language Models

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T21:15:04.067379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 54eeb67b-f683-4846-b5c7-6f591391cb73 · inbound

Are Sparse Autoencoder Benchmarks Reliable? cites this paper.

Are Sparse Autoencoder Benchmarks Reliable? Automatically Interpreting Millions of Features in Large Language Models

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-20T12:43:16.763156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e599bae1-869d-471e-af08-ac21f317a024 · inbound

Features have life history. And we should care cites this paper.

Features have life history. And we should care Automatically Interpreting Millions of Features in Large Language Models

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:33:50.874513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 7ffd95b3-ce31-4606-902a-cf1f63dc9dc1 · inbound

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization cites this paper.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Automatically Interpreting Millions of Features in Large Language Models

Reference 39

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T22:57:25.986871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 59891a17-6ca1-43c0-a706-ff00c4581768 · inbound

Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders cites this paper.

Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders Automatically Interpreting Millions of Features in Large Language Models

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T00:27:30.040455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation aca94aaf-78fb-4915-a67b-705996dd12b4 · inbound

ICA Lens: Interpreting Language Models Without Training Another Dictionary cites this paper.

ICA Lens: Interpreting Language Models Without Training Another Dictionary Automatically Interpreting Millions of Features in Large Language Models

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-03T09:17:49.074626Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b94cef44-8a3d-49b8-9a8b-b2329d44269a · inbound

Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal cites this paper.

Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal Automatically Interpreting Millions of Features in Large Language Models

Reference 76

Resolution: verified exact; arxiv_id, observed 2026-07-03T09:07:47.877710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation be03c80f-db8d-48c6-9e78-80c0d70d54a6 · inbound

Extraction and Analysis of Multimodal Concepts in Vision Language Models through Sparse Autoencoders cites this paper.

Extraction and Analysis of Multimodal Concepts in Vision Language Models through Sparse Autoencoders Automatically Interpreting Millions of Features in Large Language Models

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-06-26T14:29:31.008385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f5c018c0-08fe-4128-a372-79e995f9b0fa · inbound

Do Sparse Autoencoders Learn Meaningful Concept Hierarchies? cites this paper.

Do Sparse Autoencoders Learn Meaningful Concept Hierarchies? Automatically Interpreting Millions of Features in Large Language Models

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-07-04T10:29:45.385912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e6cb9511-ab47-4020-be0c-38adefadde2f · inbound

Training, Reading, and Editing Legible Transformers cites this paper.

Training, Reading, and Editing Legible Transformers Automatically Interpreting Millions of Features in Large Language Models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-13T05:35:58.568346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 378236f7-3528-43ed-b6df-9fe19f1c222f · inbound

Verbalizable Representations Form a Global Workspace in Language Models cites this paper.

Verbalizable Representations Form a Global Workspace in Language Models Automatically Interpreting Millions of Features in Large Language Models

Reference 139

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:30.760858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77f466a6-23af-49c0-9269-a828189cd789 · inbound

ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels cites this paper.

ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels Automatically Interpreting Millions of Features in Large Language Models

Reference 116

Resolution: unresolved; no resolver link, observed 2026-08-05T17:48:46.321102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.