SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Record

Authors
Karvonen, A.; Rager, C.; Lin, J.; Tigges, C.; Bloom, J.; et al.
Year
2025
Title
SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
Published in
arXiv
Type
Preprint
DOI
10.48550/arxiv.2503.09532
arXiv
arXiv:2503.09532
Our note
none yet
Verification
verified: its identifier resolves to a record with the same title and author (checked against OpenAlex, 2026-11-14).
Identifiers found: OpenAlex W4416070475 · DOI 10.48550/arxiv.2503.09532 · arXiv:2503.09532
From the lookup
doi (the pages' own wording is under "As cited" below)
Id
karvonen-2025-saebench-comprehensive-benchmark-sparse-autoencoders-language

Cited on

As cited

The pages cite this work in one form.

  • Karvonen, A., Rager, C., Lin, J., Tigges, C., Bloom, J., et al. (2025). SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability. Proceedings of the 42nd International Conference on Machine Learning (ICML), PMLR 267. arXiv:2503.09532.

BibLaTeX

@misc{karvonen-2025-saebench-comprehensive-benchmark-sparse-autoencoders-language,
  author = {Karvonen, A. and Rager, C. and Lin, J. and Tigges, C. and Bloom, J. and others},
  title = {{SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability}},
  date = {2025},
  doi = {10.48550/arxiv.2503.09532},
  eprint = {2503.09532},
  eprinttype = {arxiv}
}

Download · JSON with CSL-JSON · the whole bibliography