4 papers
Minimal and Mechanistic Conditions for Behavioral Self-Awareness in LLMs
Matthew Bozoukov, Matthew Nguyen, Shubkarman Singh +2
Recent studies have revealed that LLMs can exhibit behavioral self-awareness: the ability to accurately describe or predict their own learned behaviors without explicit supervision…
Learning Multi-Level Features with Matryoshka Sparse Autoencoders
Bart Bussmann, Noa Nabeshima, Adam Karvonen +1
Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting neural networks by extracting the concepts represented in their activations. However, choosing the size…
Sparse Autoencoders Do Not Find Canonical Units of Analysis
Patrick Leask, Bart Bussmann, Michael Pearce +5
A common goal of mechanistic interpretability is to decompose the activations of neural networks into features: interpretable properties of the input computed by the model. Sparse…
BatchTopK Sparse Autoencoders
Bart Bussmann, Patrick Leask, Neel Nanda
Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting language model activations by decomposing them into sparse, interpretable features. A popular approach i…