Paper Citation Record · LEDGER

Polysemanticity and Capacity in Neural Networks

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 27 inbound Pith citation observations for arXiv:2210.01892.

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

pith.paper-citation-record.v1
2210.01892 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 27 of 27 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 27 of 27 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:13:50.629906Z

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

4
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 70091f74-4373-4c53-8546-f2e5d3bb1072 · inbound

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods cites this paper.

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods Polysemanticity and Capacity in Neural Networks

Reference 110

Resolution: verified exact; arxiv_id, observed 2026-05-17T11:56:11.139782Z

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 f6c6890b-db6f-4ef9-b548-0490b1be17a4 · inbound

A Closer Look at Multimodal Representation Collapse cites this paper.

A Closer Look at Multimodal Representation Collapse Polysemanticity and Capacity in Neural Networks

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-07T13:13:50.629906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e645ddab-5db0-4af7-bacd-bae307667907 · inbound

Localizing Persona Representations in LLMs cites this paper.

Localizing Persona Representations in LLMs Polysemanticity and Capacity in Neural Networks

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T12:25:33.728567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4c88b24-1836-475f-afd1-59566a50a3d1 · inbound

DCN^2: Interplay of Implicit Collision Weights and Explicit Cross Layers for Large-Scale Recommendation cites this paper.

DCN^2: Interplay of Implicit Collision Weights and Explicit Cross Layers for Large-Scale Recommendation Polysemanticity and Capacity in Neural Networks

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T23:10:38.959206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 881f5796-2c70-4e7c-8395-272972d4f4c1 · inbound

Compressed Computation: Dense Circuits in a Toy Model of the Universal-AND Problem cites this paper.

Compressed Computation: Dense Circuits in a Toy Model of the Universal-AND Problem Polysemanticity and Capacity in Neural Networks

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:55.368683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc129477-c43d-4248-a8a0-a744e98057ff · inbound

Smaller, Faster, Cheaper: Architectural Designs for Efficient Machine Learning cites this paper.

Smaller, Faster, Cheaper: Architectural Designs for Efficient Machine Learning Polysemanticity and Capacity in Neural Networks

Reference 134

Resolution: unresolved; no resolver link, observed 2026-08-06T14:06:51.246973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9906b6d2-217a-4617-a6bc-79b3c55b5978 · inbound

How Causal Abstraction Underpins Computational Explanation cites this paper.

How Causal Abstraction Underpins Computational Explanation Polysemanticity and Capacity in Neural Networks

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-05T20:08:42.380315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd19aae6-2d35-4514-88d1-a725bd6b083a · inbound

Expand Neurons, Not Parameters cites this paper.

Expand Neurons, Not Parameters Polysemanticity and Capacity in Neural Networks

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T11:33:16.977876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0f8b374-d813-46a4-a3ac-c97ae9ac619c · inbound

Adversarial Attacks Leverage Interference Between Features in Superposition cites this paper.

Adversarial Attacks Leverage Interference Between Features in Superposition Polysemanticity and Capacity in Neural Networks

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-04T10:08:54.764366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e18cf29-c553-4e2f-8fe1-d860bb82aa99 · inbound

Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations cites this paper.

Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations Polysemanticity and Capacity in Neural Networks

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-04T09:08:58.319230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7de981cb-c30e-4e39-ac2a-3cb0bcf792e4 · inbound

CHiQPM: Calibrated Hierarchical Interpretable Image Classification cites this paper.

CHiQPM: Calibrated Hierarchical Interpretable Image Classification Polysemanticity and Capacity in Neural Networks

Reference 54

Resolution: metadata mismatch; arxiv_id, observed 2026-05-17T04:29:02.011975Z

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 a9b5c050-3d04-40bb-9bbe-bd49d12e7344 · inbound

Geometric Limits of Knowledge Distillation: A Minimum-Width Theorem via Superposition Theory cites this paper.

Geometric Limits of Knowledge Distillation: A Minimum-Width Theorem via Superposition Theory Polysemanticity and Capacity in Neural Networks

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:08:01.740854Z

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 107f1817-b263-4c77-9a76-f13b61a56e11 · 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 Polysemanticity and Capacity in Neural Networks

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-11T16:51:08.315210Z

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 d4e892b7-542f-4bf1-84c9-66543efa069d · inbound

Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction cites this paper.

Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction Polysemanticity and Capacity in Neural Networks

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-09T06:00:36.284977Z

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 63b3f8a4-c1a1-4501-a48c-92815d12865b · inbound

Structural Instability of Feature Composition cites this paper.

Structural Instability of Feature Composition Polysemanticity and Capacity in Neural Networks

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-10T06:41:36.514882Z

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 1408ede1-6a37-4ddf-8f02-11c9c6a18260 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Polysemanticity and Capacity in Neural Networks

Reference 91

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:59:28.770938Z

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 0e954b29-044e-4143-af3e-9a6f1bcb6f15 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Polysemanticity and Capacity in Neural Networks

Reference 91

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T04:59:45.283028Z

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 4be3aa81-0e14-4e56-b76c-9c565556ced6 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Polysemanticity and Capacity in Neural Networks

Reference 91

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T21:53:47.258320Z

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 d0078605-1601-4ced-85d8-c2a0e669e333 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Polysemanticity and Capacity in Neural Networks

Reference 37

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T07:49:50.197144Z

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 e6764dd1-faba-45e4-a7b2-dff545638db2 · inbound

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces cites this paper.

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces Polysemanticity and Capacity in Neural Networks

Reference 157

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T20:17:55.347084Z

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 94f10e37-3a19-4534-8432-9103f2593762 · inbound

Steered Generation via Gradient-Based Optimization on Sparse Query Features cites this paper.

Steered Generation via Gradient-Based Optimization on Sparse Query Features Polysemanticity and Capacity in Neural Networks

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-25T05:36:40.325635Z

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 ae5147c2-b29c-420b-a62d-7a9bbc0918a5 · inbound

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet cites this paper.

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet Polysemanticity and Capacity in Neural Networks

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-06-29T07:53:13.500422Z

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 4ca6bb2d-7386-43f8-baaf-d0a74c342e07 · inbound

Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance cites this paper.

Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance Polysemanticity and Capacity in Neural Networks

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:12:50.630036Z

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 5e341244-26b1-4e8f-898b-c750cac4c92e · inbound

Neuron Populations Exhibit Divergent Selectivity with Scale cites this paper.

Neuron Populations Exhibit Divergent Selectivity with Scale Polysemanticity and Capacity in Neural Networks

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:36:26.811006Z

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 dd20fc33-f153-46f2-a4fc-6192ebc63e4a · inbound

SAERec: Constructing Fine-grained Interpretable Intents Priors via Sparse Autoencoders for Recommendation cites this paper.

SAERec: Constructing Fine-grained Interpretable Intents Priors via Sparse Autoencoders for Recommendation Polysemanticity and Capacity in Neural Networks

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-07-04T02:39:25.093980Z

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 1f7c149d-6347-42e6-afe3-e08f9ee48b99 · inbound

From Weights to Features: SAE-Guided Activation Regularization for LLM Continual Learning cites this paper.

From Weights to Features: SAE-Guided Activation Regularization for LLM Continual Learning Polysemanticity and Capacity in Neural Networks

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T13:09:50.223505Z

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 12c45481-cde0-4def-98ca-5709dfeab55d · inbound

PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding cites this paper.

PairSAE: Mechanistic Interpretability from Pair Representations in Protein Co-Folding Polysemanticity and Capacity in Neural Networks

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-01T18:55:58.719403Z

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.