Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders | Paper Citation Record

Observation ffccd1ab-47e9-4fa4-a2ab-4326f1be729c · inbound

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

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 596a6086-14ec-47f8-800c-39438f1e92d4 · 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 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 68e6aca4-03a4-4a3a-89ba-c2b5f79cbd5b · inbound

Transcoders Beat Sparse Autoencoders for Interpretability cites this paper.

Transcoders Beat Sparse Autoencoders for Interpretability Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-09T22:24:53.890411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fee4390-6299-41e1-a199-52b7c4b26e79 · inbound

Low-Rank Adapting Models for Sparse Autoencoders cites this paper.

Low-Rank Adapting Models for Sparse Autoencoders Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 6014

Resolution: unresolved; no resolver link, observed 2026-08-09T20:18:31.032548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e45417b-291a-4d4a-bced-9d75e75a561d · inbound

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models cites this paper.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.796172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea790f9a-95ee-4c67-9ad7-c6dc333ae882 · inbound

Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs cites this paper.

Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T15:20:04.815226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06cee725-277b-45a1-a9c7-2dc6f15635da · 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 Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:43.148233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49a5bc79-cd46-4749-b6f5-eef6fb7db0f6 · inbound

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

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:03.074303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d2b8d8b-d715-4eb1-a70a-bb19f0608553 · inbound

Model Unlearning via Sparse Autoencoder Subspace Guided Projections cites this paper.

Model Unlearning via Sparse Autoencoder Subspace Guided Projections Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:04.084704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46932a4e-44c9-491b-9221-7b4410c8e8a2 · 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 Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:26.310145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0b3ba71-1cf0-4293-b0d4-471e776df561 · inbound

Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval cites this paper.

Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T13:26:00.004751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b333191b-fce9-4665-a040-ee7afa26b043 · inbound

Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures cites this paper.

Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T11:56:15.227935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfc83c62-feb4-4434-bd63-0fcc8d33e498 · inbound

On the transferability of Sparse Autoencoders for interpreting compressed models cites this paper.

On the transferability of Sparse Autoencoders for interpreting compressed models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T15:24:45.780183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0389f5bd-598f-4b01-b849-47e4c4b27771 · inbound

Interpreting CFD Surrogates through Sparse Autoencoders cites this paper.

Interpreting CFD Surrogates through Sparse Autoencoders Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T15:23:47.354934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92603a17-4b50-4883-aaf5-535b6e701c17 · inbound

SATORI: Static Test Oracle Generation for REST APIs cites this paper.

SATORI: Static Test Oracle Generation for REST APIs Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-05T17:26:48.663422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99b5aca8-e888-426f-8387-ad271dc4b08a · inbound

Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders cites this paper.

Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T17:18:55.529394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a74c71cc-6b9e-4dc3-823f-fc61655aa2a1 · inbound

Mechanistic Interpretability with Sparse Autoencoder Neural Operators cites this paper.

Mechanistic Interpretability with Sparse Autoencoder Neural Operators Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-18T19:01:45.810690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ba19ec6f-7a03-4ac4-8d5e-334a4332baec · 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 Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-18T18:16:43.716058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 71629dbf-e71a-4909-96da-3041d7b65bcb · inbound

Towards Atoms of Large Language Models cites this paper.

Towards Atoms of Large Language Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.200772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91f35bf3-138c-4260-a2cd-bbd6e04d4765 · 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 Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-05-18T02:00:39.998698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7841f6d3-19e6-46b5-9e28-9182d7b57ed5 · 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 Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T00:23:29.570164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c3a879d-1ead-4247-98d1-c3ea01d14302 · inbound

TimeSAE: Causal Sparse Decoding for Faithful Explanations of Black-Box Time Series Models cites this paper.

TimeSAE: Causal Sparse Decoding for Faithful Explanations of Black-Box Time Series Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-03T10:37:09.467541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e7017e5-d561-4cf6-a013-6937752fa416 · inbound

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models cites this paper.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 253

Resolution: verified exact; local_arxiv, observed 2026-05-16T12:40:54.838031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8c54f24b-752d-4be3-a289-632e01709423 · inbound

Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models cites this paper.

Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T04:36:02.058970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d09b38ea-5100-4d85-b5e9-86e02a723c37 · inbound

Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models cites this paper.

Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T06:15:56.047020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc1199ee-7b01-445c-a08f-e61a81986627 · inbound

Less is Enough: Synthesizing Diverse Data in LLM Feature Space with Sparse Autoencoders cites this paper.

Less is Enough: Synthesizing Diverse Data in LLM Feature Space with Sparse Autoencoders Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-03T01:17:12.111322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb614b8d-5c6f-49c3-9f9d-4aeea21d6f0a · 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 Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T05:36:47.915559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3294692-5b20-4f7c-96b4-2622d3a64e90 · inbound

Interpreting Video Representations with Spatio-Temporal Sparse Autoencoders cites this paper.

Interpreting Video Representations with Spatio-Temporal Sparse Autoencoders Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-13T12:01:02.997589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08f31dad-df93-40f9-a232-be3096c17256 · inbound

Sparse Autoencoders as a Steering Basis for Phase Synchronization in Graph-Based CFD Surrogates cites this paper.

Sparse Autoencoders as a Steering Basis for Phase Synchronization in Graph-Based CFD Surrogates Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 337da283-b4ec-48d6-8476-17627654de1e · inbound

Improving Robustness In Sparse Autoencoders via Masked Regularization cites this paper.

Improving Robustness In Sparse Autoencoders via Masked Regularization Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9774160d-a5fe-49f2-85e2-cee877bfbde2 · inbound

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

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 86

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bbfccfab-3731-4e59-b981-f524b3268000 · inbound

Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision cites this paper.

Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 59f4efb3-a376-40d5-a855-2fbf0081db17 · inbound

Improving Sparse Autoencoder with Dynamic Attention cites this paper.

Improving Sparse Autoencoder with Dynamic Attention Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a7d93154-2fa3-4120-b152-b28717c5ed89 · inbound

Geometric quantification for nonlinear deformation in knitted fabrics cites this paper.

Geometric quantification for nonlinear deformation in knitted fabrics Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-15T11:27:58.396234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b6af0b3-49c3-4a82-8ef9-d1007b9df886 · inbound

SAGE: Signal-Amplified Guided Embeddings for LLM-based Vulnerability Detection cites this paper.

SAGE: Signal-Amplified Guided Embeddings for LLM-based Vulnerability Detection Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7c5554f7-4bd3-4270-81fd-3466b71dace4 · inbound

GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models cites this paper.

GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation abc4f127-340f-4647-9437-33c4d6a6a197 · inbound

Feature Starvation as Geometric Instability in Sparse Autoencoders cites this paper.

Feature Starvation as Geometric Instability in Sparse Autoencoders Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5ccfc7b7-6452-47d8-b388-081865810aff · 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 Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5435b3a1-43c6-45d0-8c52-34b1329e1b41 · inbound

SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders cites this paper.

SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 309fd137-348f-4ddb-97f8-75bd2b938ce9 · inbound

SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders cites this paper.

SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 66b7d079-a146-4933-99cc-54340c862b8c · inbound

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

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e4e5d8d1-165a-413f-8a21-6869e40741c5 · inbound

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

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 17b5ff65-fd3f-4522-9692-61ae7179c0e4 · inbound

Tool Calling is Linearly Readable and Steerable in Language Models cites this paper.

Tool Calling is Linearly Readable and Steerable in Language Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 67

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0262a18d-f727-4ac6-a1a9-bc36ddd63173 · inbound

The Echo Amplifies the Knowledge: Somatic Marker Analogues in Language Models via Emotion Vector Re-Injection cites this paper.

The Echo Amplifies the Knowledge: Somatic Marker Analogues in Language Models via Emotion Vector Re-Injection Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 52a21e34-3b1f-45ba-a374-0a761ca2acb2 · inbound

Causal Dimensionality of Transformer Representations: Measurement, Scaling, and Layer Structure cites this paper.

Causal Dimensionality of Transformer Representations: Measurement, Scaling, and Layer Structure Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8960a5be-c63b-4150-a7de-69ab84b29ee9 · inbound

fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery cites this paper.

fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e455d1e3-3e69-41ce-b1ee-6b2763725e6e · inbound

Do Language Models Encode Knowledge of Linguistic Constraint Violations? cites this paper.

Do Language Models Encode Knowledge of Linguistic Constraint Violations? Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 14d03df5-f0d4-405a-be67-a7aaeebb0b4a · inbound

Do Language Models Encode Knowledge of Linguistic Constraint Violations? cites this paper.

Do Language Models Encode Knowledge of Linguistic Constraint Violations? Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation eed38736-ea99-4cf6-9833-712a0bb5d754 · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8ec875c2-38e2-4414-b60e-0e98474c540c · inbound

WriteSAE: Sparse Autoencoders for Recurrent State cites this paper.

WriteSAE: Sparse Autoencoders for Recurrent State Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:10:17.136575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f44fb20b-f387-41a9-8dc8-519f87528edc · inbound

SwordBench: Evaluating Orthogonality of Steering Image Representations cites this paper.

SwordBench: Evaluating Orthogonality of Steering Image Representations Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-05-20T22:39:09.768197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 40369072-b782-4c3e-832c-05e852df4b37 · inbound

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents cites this paper.

To Call or Not to Call: Diagnosing Intrinsic Over-Calling Bias in LLM Agents Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-20T16:08:33.493338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ff60ef5e-7c2c-42e6-ad57-fbd6764da7c8 · inbound

Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift cites this paper.

Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-22T08:16:16.105358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f3501ba7-7956-49a8-a3c1-c7579ea21f47 · inbound

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

ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-06-29T15:03:31.595393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5eabc811-0ce6-4c4c-a42b-4ee77d21449c · 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 Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-06-29T14:23:30.773044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0727cafc-bb07-44ef-8c04-3c265402295f · 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 Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T05:02:51.374685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 296ae2b3-1de0-4632-8e28-3bac0d27fb8e · inbound

Latent Terms: Dense Retrievers Contain Trivially Extractable BM25-ready Zipfian Vocabularies cites this paper.

Latent Terms: Dense Retrievers Contain Trivially Extractable BM25-ready Zipfian Vocabularies Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T05:53:09.095356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f96ee443-318d-4fa1-913b-0f4fe6323c3f · inbound

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

Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-06-29T00:12:50.644613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cbd0646c-4945-4008-b6e8-90bb467e7308 · inbound

How Far Do Auto-Interpretation Labels Generalize: A Controlled Study Across Languages, Scripts, and Rewordings cites this paper.

How Far Do Auto-Interpretation Labels Generalize: A Controlled Study Across Languages, Scripts, and Rewordings Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-07-01T19:46:11.028464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3b88cc82-de5e-4677-a434-bf576a4756e2 · inbound

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability cites this paper.

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-06-28T02:11:29.109473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a3fb4cec-7a6e-425b-b877-d5673c186c9c · inbound

Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers cites this paper.

Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 136

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T12:36:56.276823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 923a08d3-6ed5-42e5-b428-c0a7682668fa · inbound

Interpreting Brain Responses to Language with Sparse Features from Language Models cites this paper.

Interpreting Brain Responses to Language with Sparse Features from Language Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T16:57:09.608205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 039a5ef7-c614-489e-a6c0-fa325f0fcc71 · inbound

Interpreting Brain Responses to Language with Sparse Features from Language Models cites this paper.

Interpreting Brain Responses to Language with Sparse Features from Language Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-12T14:56:52.698162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e05405bd-559c-4e0c-84d1-0282fcf37feb · inbound

A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders cites this paper.

A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T16:47:09.882861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8b6d8e51-9ece-4da6-9f2b-e175cddd1831 · inbound

TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment cites this paper.

TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 276

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T16:47:10.110711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9240a820-d306-4d90-9c1f-e3f06dcce1f7 · inbound

DOME: Learning Transferable Domain Variables from Sparse Supervision for Test-Time Adaptation cites this paper.

DOME: Learning Transferable Domain Variables from Sparse Supervision for Test-Time Adaptation Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:26:26.480709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 57192785-c6c8-4249-8eaf-36776b18c026 · inbound

Pre-Intervention Prediction of Sparse Autoencoder Steering Side Effects cites this paper.

Pre-Intervention Prediction of Sparse Autoencoder Steering Side Effects Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T21:17:24.462704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dc4b13c5-85e9-40e6-b2e8-53db6cad18c9 · inbound

VFUSE: Virulent Feature Understanding with Sparse autoEncoders cites this paper.

VFUSE: Virulent Feature Understanding with Sparse autoEncoders Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-07-03T00:57:29.995949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 899dd754-a276-40ac-b687-bcae3ad5a502 · inbound

Rational Sparse Autoencoder cites this paper.

Rational Sparse Autoencoder Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:08:43.972935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c66e290b-7cd2-45b9-a981-76ba3fadb22a · inbound

On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning cites this paper.

On the Sparsity-Storage-Accuracy Tradeoff in Parsimoniously Activated Dictionary Learning Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-04T08:39:42.112598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 32a4b290-bea8-4ed8-91a3-86bb6ac222be · inbound

Steering Vision-Language Models with Joint Sparse Autoencoders cites this paper.

Steering Vision-Language Models with Joint Sparse Autoencoders Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 51

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T20:00:07.772991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bfcc3684-78be-47f5-aca1-08ed3cef8b48 · inbound

Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs cites this paper.

Where Do Models Find Happiness? Emotion Vectors in Open-Source LLMs Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T13:39:50.857990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation aa4febb4-3780-4fa3-900f-897da3ac9bf7 · inbound

Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability cites this paper.

Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:28:44.136826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e78f2644-0883-49ce-8baf-d79551aba036 · inbound

Persistent Sparse Autoencoders: Learning Feature Timescales in Language Models cites this paper.

Persistent Sparse Autoencoders: Learning Feature Timescales in Language Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-01T19:02:37.547183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5339c45-0f00-4f16-ab92-4af0d40b1028 · inbound

Decoder-Preserving Sparse Autoencoders: Which Readouts Survive Sparse Compression? cites this paper.

Decoder-Preserving Sparse Autoencoders: Which Readouts Survive Sparse Compression? Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T18:04:17.870680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7809fa3-b98e-4dc0-9ca3-5abd2b83d4aa · inbound

Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence cites this paper.

Measuring Monosemanticity in Sparse Autoencoders via Latent Activation Coherence Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T17:08:24.782022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e5ea7f8-9dd2-4201-9731-1a45f81ba0e3 · inbound

Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models cites this paper.

Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T12:14:21.082141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0a46698-b540-401b-bf2e-21daa056d903 · inbound

Beyond Liars' Bench: The Impact of Lie Typology, Depth, and Sparsity on Deception Detection in LLMs cites this paper.

Beyond Liars' Bench: The Impact of Lie Typology, Depth, and Sparsity on Deception Detection in LLMs Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T12:47:01.797511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d636f9f0-1f08-4100-9198-cce32ee61ede · inbound

Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects cites this paper.

Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-01T10:03:58.626375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec8d9df3-026d-48ff-9b8a-579559a5eb65 · inbound

Reference Feature Atlases for Mechanistic Auditing of Language Models cites this paper.

Reference Feature Atlases for Mechanistic Auditing of Language Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T12:35:17.281430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a01cabda-0f7d-446b-8dfd-a813dd223984 · inbound

CADENCE: A Cardiac Atom Dictionary for Interpretable Neural Concept Extraction from ECG Foundation Models cites this paper.

CADENCE: A Cardiac Atom Dictionary for Interpretable Neural Concept Extraction from ECG Foundation Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T03:03:59.542209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f5e4d2a-39b7-45b2-9c5a-ecaf771c9118 · inbound

Explaining Image Similarity with Automatically Extracted Concept Activation Vectors cites this paper.

Explaining Image Similarity with Automatically Extracted Concept Activation Vectors Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-31T09:04:52.357025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers