Sparse autoencoders applied to GPT-2 and Llama models recover semantic features accounting for 94% of peak brain encoding performance and map onto distinct cortical semantic regions across three languages.
and Coulson, Seana and Bergen, Benjamin K
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
A workshop synthesis provides a decomposition framework for RL-cyber environment interfaces and best-practice guidelines for training and evaluating autonomous cyber defence agents.
citing papers explorer
-
Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography
Sparse autoencoders applied to GPT-2 and Llama models recover semantic features accounting for 94% of peak brain encoding performance and map onto distinct cortical semantic regions across three languages.
-
Building Better Environments for Autonomous Cyber Defence
A workshop synthesis provides a decomposition framework for RL-cyber environment interfaces and best-practice guidelines for training and evaluating autonomous cyber defence agents.