Paper Citation Record · LEDGER

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks

As of 18 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 6 inbound Pith citation observations for arXiv:2411.18895.

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

pith.paper-citation-record.v1
2411.18895 v1

Coverage vector

measured 23 of 23 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T10:51:14.316730Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T18:21:12.948006Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T14:55:48.780229Z

Reference resolution

23 of 23 outbound references displayed

verified exact0
verified fuzzy6
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 08ee7a38-f1dc-4010-848b-77c24875ccdf · outbound

This paper cites an unresolved cited work.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-12T10:51:14.655786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 631b864c-223a-42a6-8d9b-dbd92a8bd867 · outbound

This paper cites After finishing all steps above, provide a single json block at the end of your response.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks After finishing all steps above, provide a single json block at the end of your response

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:51:14.560278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 51dc5e3e-8440-48ee-ab80-e0dd1f369222 · outbound

This paper cites professor.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks professor

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:51:14.570899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ee4f3508-a00d-48e0-8fdd-7ce01cd940b2 · outbound

This paper cites Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T10:51:14.254431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb9b0adc-7752-4c32-a0bd-73c9fa09e8a2 · outbound

This paper cites Iskander, K.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks Iskander, K

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:51:14.633741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 183c825e-488b-45a5-8b46-73504b304862 · outbound

This paper cites doi: 10.18653/v1/2023.findings-acl.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks doi: 10.18653/v1/2023.findings-acl

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T10:51:14.263070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c42952d9-cc2e-4a03-864c-6542b831e299 · outbound

This paper cites Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T10:51:14.270695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ddc2524-18e8-463c-b35b-c2e63e015bde · outbound

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

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T10:51:14.275309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9248b802-0aea-4ca6-a2aa-c38390412631 · outbound

This paper cites Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-12T10:51:14.279120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96fc5b82-4d57-440f-a233-cfe19b8b536f · outbound

This paper cites Improving Dictionary Learning with Gated Sparse Autoencoders.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks Improving Dictionary Learning with Gated Sparse Autoencoders

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T10:51:14.282912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b274823-9364-4353-bcc2-41035a3b4a5d · outbound

This paper cites doi: 10.18653/ v1/2020.acl-main.647.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks doi: 10.18653/ v1/2020.acl-main.647

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T10:51:14.286898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34d80982-8d3f-440e-b7d3-a129f3601e29 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks Gemma 2: Improving Open Language Models at a Practical Size

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-12T10:51:14.290799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38e09a5a-91d5-46c1-bb09-692a397a866a · outbound

This paper cites an unresolved cited work.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-12T10:51:14.604959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation fb0f3733-9a2d-4dc8-b83f-b479f701c548 · outbound

This paper cites doi: 10.18653/v1/2020.acl-main.484.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks doi: 10.18653/v1/2020.acl-main.484

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T10:51:14.297918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2076a55-8b73-4779-be0b-41a6a5b97f15 · outbound

This paper cites We train Vanilla and TopK architectures on 200M tokens from The Pile Gao et al.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks We train Vanilla and TopK architectures on 200M tokens from The Pile Gao et al

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:51:14.593224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b9d52eb8-3b02-4b22-a68e-c622566f9202 · outbound

This paper cites 5 Additionally, we evaluate JumpReLU SAEs from the Gemma-Scope suite Lieberum et al.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks 5 Additionally, we evaluate JumpReLU SAEs from the Gemma-Scope suite Lieberum et al

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:51:14.582043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation b8160456-0bbe-4c07-ab7b-570cf2ecae0e · outbound

This paper cites an unresolved cited work.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks Unresolved cited work

Reference 369

Resolution: unresolved; raw_fallback, observed 2026-08-12T10:51:14.622491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f8d747f4-465b-4bd8-9394-5ca465ebedd5 · outbound

This paper cites Dateline.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks Dateline

Reference 2013

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T10:51:14.548468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 28626dba-f771-4cae-b5ef-d801137be7c0 · outbound

This paper cites URL http://dx.doi.org/10.1145/3287560.3287572.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks URL http://dx.doi.org/10.1145/3287560.3287572

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-12T10:51:14.238538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0779622a-7e57-4b73-b0d0-29cf0c112045 · outbound

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

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-12T10:51:14.250312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70258dff-4239-4aa2-bbc3-815b12dc1ae0 · outbound

This paper cites an unresolved cited work.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks Unresolved cited work

Reference 2022

Resolution: unresolved; raw_fallback, observed 2026-08-12T10:51:14.644822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d2d2d430-2e1e-4a8a-aac3-80267b0cc742 · outbound

This paper cites Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-12T10:51:14.229968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b038d02-bc95-459d-9304-50022b173da5 · outbound

This paper cites A Primer on the Inner Workings of Transformer-based Language Models.

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks A Primer on the Inner Workings of Transformer-based Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-12T10:51:14.246042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

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

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words cites this paper.

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 28269566-c2a5-4d2c-8d13-1864584dd479 · inbound

Discovering Chunks in Neural Embeddings for Interpretability cites this paper.

Discovering Chunks in Neural Embeddings for Interpretability Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-09T14:29:20.016483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f992757-a0f2-4c94-8baf-fd3dd9143563 · inbound

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding cites this paper.

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T18:21:12.948006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f93244d4-e800-4a1a-95c9-e1ba6e3ff5d7 · inbound

Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE) cites this paper.

Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE) Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-20T12:18:16.569538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 580bd7ec-a465-4b4f-82dd-2fbc1e3a0164 · inbound

Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE) cites this paper.

Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE) Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-01T14:55:48.781943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2da2df48-794a-44d8-bf08-f732183a8c0f · inbound

ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions cites this paper.

ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-29T15:03:31.600144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.