Search Results for author:
Found 6 papers, 1 papers with code
Improving Dictionary Learning with Gated Sparse Autoencoders
Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by finding sparse, linear reconstructions of LM activations.
Evaluating Frontier Models for Dangerous Capabilities
To understand the risks posed by a new AI system, we must understand what it can and cannot do.
AtP*: An efficient and scalable method for localizing LLM behaviour to components
We investigate Attribution Patching (AtP), a fast gradient-based approximation to Activation Patching and find two classes of failure modes of AtP which lead to significant false negatives.
Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla
\emph{Circuit analysis} is a promising technique for understanding the internal mechanisms of language models.
Progress measures for grokking via mechanistic interpretability
Based on this understanding, we define progress measures that allow us to study the dynamics of training and split training into three continuous phases: memorization, circuit formation, and cleanup.
Retrospective on the 2021 BASALT Competition on Learning from Human Feedback
The goal of the competition was to promote research towards agents that use learning from human feedback (LfHF) techniques to solve open-world tasks.
