Scaling and evaluating sparse autoencoders

Open Webpage

Leo Gao, Tom Dupré la Tour, Henk Tillman, Gabriel Goh, Rajan Troll, Alec Radford, Ilya Sutskever, Jan Leike, Jeffrey Wu

Published: 01 Jan 2025, Last Modified: 16 May 2025ICLR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0