Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-06T22:48:39.789242Z
Paper Citation Record · LEDGER
As of 7 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 11 inbound Pith citation observations for arXiv:2506.20790.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-06T22:48:39.789242Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-02T10:40:00.923289Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z
45 of 45 outbound references displayed
External citation measurements
0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z
Observation 54a6e163-e3c8-4e2d-bf1e-2a0f62b37722 · outbound
Stochastic Parameter Decomposition Sanity checks for saliency maps
Reference 1
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e8ede1bc-94ea-4eb0-8772-c9ee9a14206b · outbound
Stochastic Parameter Decomposition Compressed computation is (probably) not computation in superposition
Reference 2
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 949792ff-a09c-423b-af8d-70de132f16cb · outbound
Stochastic Parameter Decomposition Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 473b8bdb-6098-4639-87b9-10faeaa11293 · outbound
Stochastic Parameter Decomposition Towards monosemanticity: Decomposing language models with dictionary learning
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 7b8617a8-a9e2-4799-98ea-716abd58697b · outbound
Stochastic Parameter Decomposition Low-Complexity Probing via Finding Subnetworks
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0e9a370f-c4fd-4341-ba3c-d2a7f2d762c7 · outbound
Stochastic Parameter Decomposition Causal scrubbing: a method for rigorously testing interpretability hypotheses [redwood research], December 2022
Reference 6
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4ed8260f-99e3-4f45-91b2-9f77d7230966 · outbound
Stochastic Parameter Decomposition A is for absorption: Studying feature splitting and absorption in sparse autoencoders, 2024
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9ca54fbb-1180-43f0-bd80-80f9c2de34d3 · outbound
Stochastic Parameter Decomposition Identifying Sparsely Active Circuits Through Local Loss Landscape Decomposition
Reference 8
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 30ca9bbe-f754-4aaf-a407-ba8b25890af0 · outbound
Stochastic Parameter Decomposition Towards automated circuit discovery for mechanistic interpretability
Reference 9
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 7826911e-2747-48c7-9f27-7c5797062386 · outbound
Stochastic Parameter Decomposition Are neural nets modular? inspecting functional modularity through differentiable weight masks
Reference 10
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a1b0142b-b25b-42d8-928f-7a6431bbc4f5 · outbound
Stochastic Parameter Decomposition Sparse autoencoders find highly interpretable features in language models
Reference 11
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f559adc4-cc61-48fc-bd4b-d5b0fd882561 · outbound
Stochastic Parameter Decomposition Toy models of superposition, 2022
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2ed6da7f-94bc-4eab-bcd8-1ea49fd09017 · outbound
Stochastic Parameter Decomposition Fong and Andrea Vedaldi
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b83af3fa-989b-4796-ad0a-96bbf770e3ba · outbound
Stochastic Parameter Decomposition Scaling and evaluating sparse autoencoders
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5c6ddc31-b150-4dcb-9443-3c4e9822265b · outbound
Stochastic Parameter Decomposition Causal abstractions of neural networks
Reference 15
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 19724892-987f-4aad-858c-ba3ba72c6d98 · outbound
Stochastic Parameter Decomposition Finding alignments between interpretable causal variables and distributed neural representations
Reference 16
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 6badff65-d76c-4496-9dcb-d997f27ab3a3 · outbound
Stochastic Parameter Decomposition Mathematical Models of Computation in Superposition
Reference 17
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ba4199e9-e50d-48d1-8438-e06d07c89534 · outbound
Stochastic Parameter Decomposition Tanh penalty in dictionary learning
Reference 18
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4bd9b1cd-0e62-47b6-8c04-948745103bc9 · outbound
Stochastic Parameter Decomposition Auto-Encoding Variational Bayes
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 730a5abb-3bfe-4ef2-9158-8b517b1b6833 · outbound
Stochastic Parameter Decomposition AtP*: An efficient and scalable method for localizing LLM behaviour to components
Reference 20
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 50f4f490-74c5-4fce-b7d5-385ecd300fd4 · outbound
Stochastic Parameter Decomposition Sparse Autoencoders Do Not Find Canonical Units of Analysis
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fed3fb4e-67b9-4fd7-b803-621195a5ff80 · outbound
Stochastic Parameter Decomposition Unresolved cited work
Reference 22
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3b1d973c-3ace-4b73-bd42-03db5207808b · outbound
Stochastic Parameter Decomposition Sparse crosscoders for cross-layer features and model diffing, October 2024
Reference 23
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e1de3aa5-9a2e-4ac9-8c99-61bc9acc8fdd · outbound
Stochastic Parameter Decomposition Decoupled Weight Decay Regularization
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bdb374e0-7722-4c67-bd31-b761239b2f73 · outbound
Stochastic Parameter Decomposition Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
Reference 25
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 47b92a2d-d7fd-49e9-b7b7-a886adbd62bf · outbound
Stochastic Parameter Decomposition Uncovering Model Processing Strategies with Non-Negative Per-Example Fisher Factorization
Reference 26
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ea77dc54-f757-4f79-9f4f-b874498d7399 · outbound
Stochastic Parameter Decomposition The Hydra Effect: Emergent Self-repair in Language Model Computations
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b942730d-5491-4041-9804-2ba9daf1c118 · outbound
Stochastic Parameter Decomposition SAE feature geometry is outside the superposition hypothesis
Reference 28
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation def64e53-3f7f-4e39-ab48-e6242bf5167c · outbound
Stochastic Parameter Decomposition Skeletonization: A technique for trimming the fat from a network via relevance assessment
Reference 29
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 00b14dc8-05a0-43d1-a9fb-2723150541b9 · outbound
Stochastic Parameter Decomposition Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpreting Neural Networks
Reference 30
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2a64b360-5f13-4001-8f69-97f4a51e5857 · outbound
Stochastic Parameter Decomposition The quest for the right mediator: A history, survey, and theoretical grounding of causal interpretability, 2024
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b0763e66-0360-4be6-b305-b5ea269b535b · outbound
Stochastic Parameter Decomposition Taking features out of superposition with sparse autoencoders, Dec 2022
Reference 32
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c51c0ec3-ae89-4f7d-9ea1-328ace5d5dc0 · outbound
Stochastic Parameter Decomposition Open Problems in Mechanistic Interpretability
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0b7f1b08-9636-4fd8-a7f4-dbb0a77690bf · outbound
Stochastic Parameter Decomposition Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Reference 34
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 23190b47-15e4-4206-86b3-75f223f67a5f · outbound
Stochastic Parameter Decomposition Axiomatic attribution for deep networks, 2017
Reference 35
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1109f075-260e-4bd1-b91d-580ce8ab9e1a · outbound
Stochastic Parameter Decomposition Attribution patching outperforms automated circuit discovery
Reference 36
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 004ca524-85fb-41f7-bf6b-a0ada703a170 · outbound
Stochastic Parameter Decomposition true features
Reference 37
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 951b0ab8-6f20-4813-ab74-ec5c0e9b201e · outbound
Stochastic Parameter Decomposition Investigating gender bias in language models using causal mediation analysis
Reference 38
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 33004008-74e1-4aac-af6d-2d62d86b86e2 · outbound
Stochastic Parameter Decomposition Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient
Reference 39
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 39793d58-ccfa-490b-b150-96a62e62d4c3 · outbound
Stochastic Parameter Decomposition Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
Reference 40
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 71865d85-c3cb-45d3-a446-9c2a5971dba1 · outbound
Stochastic Parameter Decomposition Algebraic geometry and statistical learning theory, volume 25
Reference 41
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c4b49939-da41-47c9-9f56-fee456421213 · outbound
Stochastic Parameter Decomposition Unresolved cited work
Reference 42
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9f35b20c-88a7-4496-b81f-ad8cdecb91f6 · outbound
Stochastic Parameter Decomposition Addressing feature suppression in saes, Feb 2024
Reference 43
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 698234ca-56f5-4be9-b715-d54f36a13c3c · outbound
Stochastic Parameter Decomposition Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors
Reference 44
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5dc92bdd-f68c-494a-a6f3-30569912dfa2 · outbound
Stochastic Parameter Decomposition Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?
Reference 45
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation d5aa0f66-4982-42ae-a757-36fb0eb11904 · inbound
Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks Stochastic Parameter Decomposition
Reference 8
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 635692dd-7338-4947-9893-7eb09eac0bed · inbound
From Mechanistic to Compositional Interpretability Stochastic Parameter Decomposition
Reference 8
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 03d47bce-22fa-42a9-965e-c926d1f8f765 · inbound
WriteSAE: Sparse Autoencoders for Recurrent State Stochastic Parameter Decomposition
Reference 97
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 303ffc89-cde7-48a5-aaaa-b84c663ed895 · inbound
WriteSAE: Sparse Autoencoders for Recurrent State Stochastic Parameter Decomposition
Reference 97
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 3e71731a-7fab-48b3-a58c-8434c0db2257 · inbound
WriteSAE: Sparse Autoencoders for Recurrent State Stochastic Parameter Decomposition
Reference 97
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ced2745a-970a-4812-a4a3-1996d6dc5a31 · inbound
WriteSAE: Sparse Autoencoders for Recurrent State Stochastic Parameter Decomposition
Reference 5
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 49d45cba-f49b-4a55-b3e7-ae521639c81f · inbound
Building Better Activation Oracles Stochastic Parameter Decomposition
Reference 20
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c9dafc5b-4505-4c87-b8e1-625ceb6dbefe · inbound
Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier Stochastic Parameter Decomposition
Reference 193
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9ca8ea7a-716c-4ebb-827f-b60ab0223303 · inbound
Individual Parameters in Weight-Sparse Transformers Appear Interpretable Stochastic Parameter Decomposition
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5735517c-11ba-426d-9c6b-f7deac5e27e6 · inbound
Targeted Recovery of Weight-Space Mechanisms From Neural Networks Stochastic Parameter Decomposition
Reference 35
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ad597dcb-af62-4e73-b2df-97c426d8dd79 · inbound
Targeted Recovery of Weight-Space Mechanisms From Neural Networks Stochastic Parameter Decomposition
Reference 152
Source-reported events for the cited work
Unavailable: canonical work link unavailable.