Paper Citation Record · LEDGER

An Interpretability Illusion for BERT

As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 17 inbound Pith citation observations for arXiv:2104.07143.

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

pith.paper-citation-record.v1
2104.07143 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 17 of 17 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T04:25:05.642287Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T12:46:57.379107Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation a175f726-d97d-4094-8d9e-db3489192e8d · inbound

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

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small An Interpretability Illusion for BERT

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.507126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 30bde55e-1f39-443b-ae73-d4fad517bce7 · inbound

Localizing Model Behavior with Path Patching cites this paper.

Localizing Model Behavior with Path Patching An Interpretability Illusion for BERT

Reference 31

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T19:38:37.786625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 54bdea91-580e-4f4f-8ca2-32e2a07e3f68 · inbound

Improving Dictionary Learning with Gated Sparse Autoencoders cites this paper.

Improving Dictionary Learning with Gated Sparse Autoencoders An Interpretability Illusion for BERT

Reference 202

Resolution: verified exact; arxiv_id, observed 2026-05-17T19:42:32.035453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3cee2c1b-c56f-4e33-a67e-0590ee663b44 · inbound

Scaling and evaluating sparse autoencoders cites this paper.

Scaling and evaluating sparse autoencoders An Interpretability Illusion for BERT

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T17:47:23.139629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5999d966-490f-4f43-b9f2-9921abce60fc · inbound

Towards Utilising a Range of Neural Activations for Comprehending Representational Associations cites this paper.

Towards Utilising a Range of Neural Activations for Comprehending Representational Associations An Interpretability Illusion for BERT

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T20:07:22.247527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be99f224-566d-4813-8519-f3251303824a · inbound

Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models cites this paper.

Incremental Sentence Processing Mechanisms in Autoregressive Transformer Language Models An Interpretability Illusion for BERT

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T20:54:02.110439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20d6f206-4a8f-4290-84b2-4b636a1693a5 · inbound

Inferring Functionality of Attention Heads from their Parameters cites this paper.

Inferring Functionality of Attention Heads from their Parameters An Interpretability Illusion for BERT

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T14:29:42.724227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eff1370b-756b-4a39-a1e1-b341cef9d4f2 · inbound

The Heap: A Contamination-Free Multilingual Code Dataset for Evaluating Large Language Models cites this paper.

The Heap: A Contamination-Free Multilingual Code Dataset for Evaluating Large Language Models An Interpretability Illusion for BERT

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T19:50:26.272331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 777759fa-b0ae-43f2-a7fd-eb557a7d9d8e · inbound

Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning cites this paper.

Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning An Interpretability Illusion for BERT

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T17:58:33.827272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87cc22af-9945-4683-b20e-ef73fe38ec6a · inbound

Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii cites this paper.

Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii An Interpretability Illusion for BERT

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T04:25:05.642287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a67009e-afc0-4b94-9e35-3417fcd244a6 · inbound

Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints cites this paper.

Recovering Event Probabilities from Large Language Model Embeddings via Axiomatic Constraints An Interpretability Illusion for BERT

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T22:41:50.729699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1b8db61-ae1a-4685-a0a9-8957651cb965 · inbound

Evaluating Neuron Explanations: A Unified Framework with Sanity Checks cites this paper.

Evaluating Neuron Explanations: A Unified Framework with Sanity Checks An Interpretability Illusion for BERT

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T10:18:24.712297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35896df0-11a0-4992-afe6-415d35e253b0 · inbound

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations cites this paper.

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations An Interpretability Illusion for BERT

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-29T14:23:30.778853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f25ab80d-7a18-4e33-9c39-bcd4f3b98a1f · inbound

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations cites this paper.

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations An Interpretability Illusion for BERT

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T05:02:51.278375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6f48bcd-4a4f-4411-b962-b0732e2f3383 · inbound

Many Circuits, One Mechanism: Input Variation and Evaluation Granularity in Circuit Discovery cites this paper.

Many Circuits, One Mechanism: Input Variation and Evaluation Granularity in Circuit Discovery An Interpretability Illusion for BERT

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-02T12:46:57.380709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 677968aa-ccce-4f23-bd82-78289adf54e4 · inbound

The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators cites this paper.

The Entanglement Wall: Activation-Space Probes as Risk Detectors, Not Context Adjudicators An Interpretability Illusion for BERT

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-02T07:09:29.963193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03de5da2-0cbf-40a8-914d-212329928d9e · inbound

Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation cites this paper.

Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation An Interpretability Illusion for BERT

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-14T13:29:00.034692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.