Joseph Isaac Bloom

ContextBench: Modifying Contexts for Targeted Latent Activation and Behaviour Elicitation

A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders

A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders

Sparse Autoencoders Do Not Find Canonical Units of Analysis

SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Interpreting Attention Layer Outputs with Sparse Autoencoders