"Is This the Subspace You Are Looking for? An Interpretability Illusion for ..."

Aleksandar Makelov, Georg Lange, Neel Nanda (2023)

Details and statistics

DOI: 10.48550/ARXIV.2311.17030

access: open

type: Informal or Other Publication

metadata version: 2023-12-04

a service of  Schloss Dagstuhl - Leibniz Center for Informatics