paper7Updated Nov 21, 2026 · Português
← All papers

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

Adam Karvonen, Can Rager, Johnny Lin, Curt Tigges, Joseph Bloom, Chanin, David, Lau, Yeu-Tong, Farrell, Eoin and 7 more

Who it is from

  • Anthropicaffiliation declared by the authors, according to OpenAlex

Other papers from the same organizations