Lange, Georg
- Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching
2023/11/28 by Makelov, Aleksandar, Lange, Georg, Nanda, Neel · 7 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)