SAE Models & Checkpoints Collection Original sparse autoencoder checkpoints and model resources used by SAEBase. • 5 items • Updated 4 days ago
Behavioral Compositionality of SAE Representations Collection Research, benchmarks, and tools for measuring how sparse autoencoder features interact to shape model behavior. • 2 items • Updated 4 days ago • 1
SAE Benchmarks, Datasets & Models Collection Benchmarks, datasets, and pretrained models for reproducible sparse autoencoder research, feature interventions, and mechanistic interpretability. • 11 items • Updated 4 days ago • 1
OpenSAE Infrastructure & Evaluation Collection Reproducible tools and evidence for sparse autoencoder research • 3 items • Updated 4 days ago
Quantification and Analysis of Layer-wise and Pixel-wise Information Discarding Paper • 1906.04109 • Published Jun 13, 2022