Cite
Notes
Only stored in your browser.
Attribution
SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
arXiv 2025
A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
arXiv 2024
from 2 papers
David Chanin
Adam Karvonen
Arthur Conmy
Callum McDougall
Can Rager
Curt Tigges
Eoin Farrell
Hardik Bhatnagar
James Wilken-Smith
Johnny Lin