Georg Lange

Publication Activity (10 Years)

Years Active: 2023-2024
Publications (10 Years): 3

Top Topics

Linear Subspace

Principal Components Analysis

Top Venues

Publications

Aleksandar Makelov, Georg Lange, Atticus Geiger, Neel Nanda
Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching. ICLR (2024)
Aleksandar Makelov, Georg Lange, Neel Nanda
Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control. CoRR (2024)
Aleksandar Makelov, Georg Lange, Neel Nanda
Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching. CoRR (2023)