Paper Citation Record · LEDGER

SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data

As of 17 August 2026, this Paper Citation Record lists 4 of 4 outbound references and 4 inbound Pith citation observations for arXiv:2602.14687.

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

pith.paper-citation-record.v1
2602.14687 v2

Coverage vector

measured 4 of 4 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T23:11:40.919297Z

measured 8 of 8 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T21:13:01.880935Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T12:59:53.069904Z

Reference resolution

4 of 4 outbound references displayed

verified exact0
verified fuzzy0
unresolved3
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c9764411-f90e-40c6-ae1f-65626c554a18 · outbound

This paper cites JumpReLU.

SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data JumpReLU

Reference 2000

Resolution: malformed identifier; no resolver link, observed 2026-08-02T23:11:40.919297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78871803-e22f-4c67-beb9-a349a80cbf2d · outbound

This paper cites Toy Models of Superposition.

SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data Toy Models of Superposition

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-02T23:11:40.595812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13a94868-c123-4ba7-94a8-b78f28b907d9 · outbound

This paper cites Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry.

SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-02T23:11:40.698377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81639659-36af-4a6f-86d8-d32d98d9d57e · outbound

This paper cites Are Sparse Autoencoders Useful? A Case Study in Sparse Probing.

SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data Are Sparse Autoencoders Useful? A Case Study in Sparse Probing

Reference 8856

Resolution: unresolved; no resolver link, observed 2026-08-02T23:11:40.793678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 5399ee43-9e5e-4812-9be5-8786f43b1300 · inbound

The Rate-Distortion-Polysemanticity Tradeoff in SAEs cites this paper.

The Rate-Distortion-Polysemanticity Tradeoff in SAEs SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-14T02:20:24.804565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b41ea254-a316-469c-85a0-f39966529b97 · inbound

Are Sparse Autoencoder Benchmarks Reliable? cites this paper.

Are Sparse Autoencoder Benchmarks Reliable? SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-14T02:20:24.804565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0f3217dc-8fa6-449c-afb1-94fb0de6f878 · inbound

Critical Percolation as a Synthetic Data Model for Interpretability cites this paper.

Critical Percolation as a Synthetic Data Model for Interpretability SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-07-14T02:20:24.804565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c93c5d17-9478-46aa-b547-2f217f10ee20 · inbound

Discovering Millions of Interpretable Features with Sparse Autoencoders cites this paper.

Discovering Millions of Interpretable Features with Sparse Autoencoders SynthSAEBench: Evaluating Sparse Autoencoders on Scalable Realistic Synthetic Data

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-14T02:20:24.804565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.