Original sparse autoencoder checkpoints and model resources used by SAEBase.
AI & ML interests
Building open foundations for understanding and evaluating LLMs.
Recent Activity
View all activity
Papers
Behavioral Compositionality of Sparse Autoencoder Representations
Representation Redistribution in Sparse Autoencoders
Original sparse autoencoder checkpoints and model resources used by SAEBase.
Reproducible tools and evidence for sparse autoencoder research
Benchmarks, datasets, and pretrained models for reproducible sparse autoencoder research, feature interventions, and mechanistic interpretability.
Research, benchmarks, and tools for measuring how sparse autoencoder features interact to shape model behavior.