5 papers
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
Tomek Korbak, Mikita Balesni, Elizabeth Barnes +38
AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known A…
A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
David Chanin, James Wilken-Smith, Tomáš Dulka +3
Sparse Autoencoders (SAEs) aim to decompose the activation space of large language models (LLMs) into human-interpretable latent directions or features. As we increase the number o…
SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
Adam Karvonen, Can Rager, Johnny Lin +12
Sparse autoencoders (SAEs) are a popular technique for interpreting language model activations, and there is extensive recent work on improving SAE effectiveness. However, most pri…
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…
Open Problems in Mechanistic Interpretability
Lee Sharkey, Bilal Chughtai, Joshua Batson +26
Mechanistic interpretability aims to understand the computational mechanisms underlying neural networks' capabilities in order to accomplish concrete scientific and engineering goa…