"Engineering Monosemanticity in Toy Models."

Adam S. Jermyn, Nicholas Schiefer, Evan Hubinger (2022)

Details and statistics

DOI: 10.48550/ARXIV.2211.09169

access: open

type: Informal or Other Publication

metadata version: 2022-11-23

a service of  Schloss Dagstuhl - Leibniz Center for Informatics