Paper Citation Record · LEDGER

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words

As of 20 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 2 inbound Pith citation observations for arXiv:2501.06254.

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

pith.paper-citation-record.v1
2501.06254 v2

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T21:28:16.065859Z

measured 47 of 47 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 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T18:47:45.375094Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T21:15:04.055124Z

Reference resolution

45 of 45 outbound references displayed

verified exact0
verified fuzzy11
unresolved34
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cc4e984b-33c7-4f71-9478-27ff0f584fda · outbound

This paper cites Mechanistic interpretability for AI safety - a review.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Mechanistic interpretability for AI safety - a review

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:28:16.857432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3b814fd9-f599-4004-823e-04e7403f66f0 · outbound

This paper cites Pythia: A suite for analyzing large language models across training and scaling.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Pythia: A suite for analyzing large language models across training and scaling

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.842557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a08aa4bf-cca9-408f-a4a9-43899f3da6a1 · outbound

This paper cites Towards monosemanticity: Decomposing language models with dictionary learning.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Towards monosemanticity: Decomposing language models with dictionary learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.848051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff5e80dd-be4e-44cc-9920-963f851b0309 · outbound

This paper cites Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.853085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b267948a-e41a-4928-89c5-7209fa478ef8 · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.858559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16a6db1e-75a5-46a5-8d12-d7e5299d1de1 · outbound

This paper cites Interpreting and steering features in images, 2024.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Interpreting and steering features in images, 2024

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:28:16.816504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4e7bb341-b664-412c-a0a2-7fd4bcdc3c0c · outbound

This paper cites Toy models of superposition.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Toy models of superposition

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.870559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 970fa9b9-db1e-4fac-a602-19671ceb57a0 · outbound

This paper cites JumpReLU: A Retrofit Defense Strategy for Adversarial Attacks.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words JumpReLU: A Retrofit Defense Strategy for Adversarial Attacks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.876363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02ed482f-ad9e-42c3-aded-4d4ca215d020 · outbound

This paper cites Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.881619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81e8df3a-b4bc-4ca7-b374-d7c5599d98db · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Scaling and evaluating sparse autoencoders

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.887335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0bcaa25-0bea-4321-b351-0b0694d112d8 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Gemma: Open Models Based on Gemini Research and Technology

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.892190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f2cd971-2d58-43c8-9e55-cc1d6327c0e9 · outbound

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

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Finding Neurons in a Haystack: Case Studies with Sparse Probing

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.897390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 297934e4-6121-4421-9d77-4589a307d0f2 · outbound

This paper cites Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.902165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edec0ad7-d7bf-44d3-a7ab-012dca57712a · outbound

This paper cites Ghost grads: An improvement on resampling.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Ghost grads: An improvement on resampling

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:28:16.785387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4711a0d7-6c4a-4d35-a5bd-14bba94ada80 · outbound

This paper cites Saebench: A comprehensive benchmark for sparse autoencoders, 2024 a.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Saebench: A comprehensive benchmark for sparse autoencoders, 2024 a

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:28:16.769395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0debf41d-2271-46f6-884f-9bef3784adb7 · outbound

This paper cites Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.916578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7610f609-cf6d-4d13-aada-894e10abdfa1 · outbound

This paper cites Interpreting Attention Layer Outputs with Sparse Autoencoders.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Interpreting Attention Layer Outputs with Sparse Autoencoders

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.921569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83307935-0e9c-43dd-a3b5-523394c7b517 · outbound

This paper cites Gazing in the latent space with sparse autoencoders.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Gazing in the latent space with sparse autoencoders

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:28:16.752811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e84e1afb-5a51-423f-962d-6d65c12a9ae2 · outbound

This paper cites The Geometry of Concepts: Sparse Autoencoder Feature Structure.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words The Geometry of Concepts: Sparse Autoencoder Feature Structure

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.932223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b30ba452-01ef-4467-ba58-f27932b2d58d · outbound

This paper cites Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.937204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de2a5c91-fb68-4c4e-b887-448a37b15947 · outbound

This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.942151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f15ea0c9-eef9-4353-b38c-3cdb31ab3af3 · outbound

This paper cites Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.947037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a79cda67-dc31-4687-ba63-98afb01110d1 · outbound

This paper cites Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.951939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e7dc628-b26d-43a5-bd8a-16342189fa84 · outbound

This paper cites Progress measures for grokking via mechanistic interpretability.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Progress measures for grokking via mechanistic interpretability

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.957051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13744a5e-33de-4ac7-85e9-5c9ad6bb8fa8 · outbound

This paper cites interpreting gpt: the logit lens.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words interpreting gpt: the logit lens

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:28:16.736846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1cef830c-a104-4898-8b9c-56cf0b1aa796 · outbound

This paper cites Zoom in: An introduction to circuits.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Zoom in: An introduction to circuits

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:28:16.720190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation abe6630a-74d8-4096-9ae8-a8032ec724da · outbound

This paper cites WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.971306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37181764-fde1-408a-a9b1-0f989ed3b46f · outbound

This paper cites Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.975906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9cb7fd5-a01b-4878-9af2-bb33f1531de9 · outbound

This paper cites Language models are unsupervised multitask learners, 2019.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Language models are unsupervised multitask learners, 2019

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.980983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5bf6374-ad56-4d9c-aa5f-43fb62817d81 · outbound

This paper cites XL - W i C : A multilingual benchmark for evaluating semantic contextualization.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words XL - W i C : A multilingual benchmark for evaluating semantic contextualization

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:28:16.692425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 745d2a4b-74ce-4277-bec0-97532b2831b9 · outbound

This paper cites Improving Dictionary Learning with Gated Sparse Autoencoders.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Improving Dictionary Learning with Gated Sparse Autoencoders

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.991035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 596a6086-14ec-47f8-800c-39438f1e92d4 · outbound

This paper cites Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:15.996362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9768eeb9-2c9a-433d-8cc7-f2c85ae6c26d · outbound

This paper cites Interpreting preference models w/ sparse autoencoders, 2024.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Interpreting preference models w/ sparse autoencoders, 2024

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:28:16.675627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f7f4036e-b3a8-4fc2-bbc5-3f5eeb9a67dd · outbound

This paper cites IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:16.007497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41906680-b897-405f-b028-15bd6191c3e0 · outbound

This paper cites Taking features out of superposition with sparse autoencoders, 2022.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Taking features out of superposition with sparse autoencoders, 2022

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:28:16.658036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5d953090-0072-46ce-8402-4facfbf74a64 · outbound

This paper cites On the proper treatment of connectionism.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words On the proper treatment of connectionism

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T21:28:16.639124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 06033563-db10-4f6b-899c-b5c470fe7559 · outbound

This paper cites Unpacking sdxl turbo: Interpreting text-to-image models with sparse autoencoders.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Unpacking sdxl turbo: Interpreting text-to-image models with sparse autoencoders

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:16.022925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2956a9d6-c3cc-4d02-88a6-69e2ddd75bf9 · outbound

This paper cites Daniel Freeman, Theodore R.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Daniel Freeman, Theodore R

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:16.027810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca6413c9-4eec-4a01-821a-2a6ab10e8abd · outbound

This paper cites SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:16.032677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 506f5d05-097b-47e5-8de2-c7c498d0d4b7 · outbound

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

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:16.037905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64baeab7-5868-40c3-b5ed-404054ea7e1a · outbound

This paper cites RedPajama: an Open Dataset for Training Large Language Models.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words RedPajama: an Open Dataset for Training Large Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:16.043585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 406ead5a-3daa-4ab3-96b1-6ae4ebe401dd · outbound

This paper cites write newline.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words write newline

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:16.048212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad7fbe71-11e6-483d-b09a-89ff751fc05d · outbound

This paper cites @esa (Ref.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words @esa (Ref

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:16.054194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c407f0f-5cda-43fc-b145-314012176faf · outbound

This paper cites an unresolved cited work.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:16.059773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 517a21a2-09b3-465a-9577-f83bf1f7a06f · outbound

This paper cites an unresolved cited work.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:16.065859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation ff612882-61eb-4bd9-a2c0-f3583fd53bc3 · inbound

Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation cites this paper.

Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words

Reference 105

Resolution: unresolved; no resolver link, observed 2026-08-05T18:47:45.375094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77fa3917-5a51-404d-a2af-bb338a0d669a · inbound

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

The Rate-Distortion-Polysemanticity Tradeoff in SAEs Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-06-30T21:15:04.057117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.