Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-05T17:18:56.858736Z
Paper Citation Record · LEDGER
As of 7 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 2 inbound Pith citation observations for arXiv:2508.16560.
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 2026-08-05T17:18:56.858736Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-05T17:26:48.667582Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-02T01:36:25.794218Z
23 of 23 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation ea91efb9-c09b-47e8-970d-cccdc32e32e5 · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders Feature hedging: Correlated features break narrow sparse autoencoders.arXiv preprint arXiv:2505.11756,
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5c05d986-410d-4ef0-b766-33eb185b1a40 · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders Dictionary learning optimization techniques.https: //transformer-circuits.pub/2025/january-update,
Reference 5
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f0e611eb-21d1-488a-91b6-ac57c2747d49 · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders The Llama 3 Herd of Models
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5a2fde88-c213-45d6-b2c7-4630a1c72e8b · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders The Pile: An 800GB Dataset of Diverse Text for Language Modeling
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 85e4a851-3abf-439e-8848-9eda8427f7e1 · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders Are Sparse Autoencoders Useful? A Case Study in Sparse Probing
Reference 10
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 17437237-317a-4538-84de-91207aabd307 · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders Adam: A Method for Stochastic Optimization
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 99b5aca8-e888-426f-8387-ad271dc4b08a · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation beab2e75-a3f0-4462-af17-39b6f5dce6a8 · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders Gemma 2: Improving Open Language Models at a Practical Size
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5f90aaef-7103-4c7f-a616-dc6de6694890 · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 525d2484-d664-4c1a-a87e-d8cd12acdb0d · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders Unresolved cited work
Reference 15
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 239fed1d-0bc9-4536-9b64-629195747781 · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders For BatchTopK SAEs, there is no sparsity penalty as sparsity is enforced by the BatchTopK function
Reference 16
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4a8456d8-9368-475d-a7eb-61530f26297d · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders We use a learning rate of3e −4 with no warmup or decay
Reference 17
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d987020c-7963-48b9-bb95-b9b2ee45d246 · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders The metric is minimized at the true L0
Reference 18
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6919888b-c2b2-4854-9f47-0059caaf9dce · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders We include all SAEs cross-listed in both SAELens and Neuronpedia with an L0 reported in SAELens
Reference 19
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8dc7b0e2-e097-45f2-bea0-1b5457b6d0f3 · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders However, we find that most open-source SAEs have L0 below 100, much lower than our analysis expects to be ideal
Reference 20
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4fbd6256-801c-46a9-8c34-eebb4dfd2ef2 · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders elbow” point, but the “elbow
Reference 21
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a44e8dae-29e9-4470-863e-96abbc676ec7 · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders Unresolved cited work
Reference 22
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b65905ce-f407-444d-8b5a-fdc66c4b27fb · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders The threshold for BatchTopK is much higher than it is for JumpReLU, and the threshold decreases as L0 increses
Reference 23
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5400b549-3046-479c-8abe-3340cb3bbf18 · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders Scaling and evaluating sparse autoencoders
Reference 2020
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ba039a99-074f-4e6d-bd04-a9cf50401773 · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders Decomposing The Dark Matter of Sparse Autoencoders
Reference 2022
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c0c8dfd4-f44e-49bd-9257-744ca2bd4923 · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders BatchTopK Sparse Autoencoders
Reference 2023
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dd93be14-1c3c-4914-b46a-4a3b389dff4b · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders Learning Multi-Level Features with Matryoshka Sparse Autoencoders
Reference 2024
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e9240924-e2ae-45e8-81d5-21e6a10bb076 · outbound
Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders A is for absorption: Studying feature splitting and absorption in sparse autoencoders.arXiv preprint arXiv:2409.14507,
Reference 2025
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5582e680-8fbd-4b78-9a34-99908386a6a4 · inbound
SATORI: Static Test Oracle Generation for REST APIs Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders
Reference 60
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dfa80f82-a054-4b72-a244-305da658db4a · inbound
Perplexity Can Miss SAE Feature Damage Under Quantization Sparse but Wrong: Incorrect L0 Leads to Incorrect Features in Sparse Autoencoders
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.