OpenSAE

Team

non-profit

https://github.com/OpenSAE

Activity Feed

AI & ML interests

Building open foundations for understanding, evaluating, and intervening in neural networks.

Recent Activity

Hunter26666666 authored a paper about 3 hours ago

Quantification and Analysis of Layer-wise and Pixel-wise Information Discarding

Hunter26666666 authored a paper about 3 hours ago

Explaining AlphaGo: Interpreting Contextual Effects in Neural Networks

Hunter26666666 authored a paper about 3 hours ago

Rotation-Equivariant Neural Networks for Privacy Protection

View all activity

Papers

Behavioral Compositionality of Sparse Autoencoder Representations

View all Papers

Hunter26666666

authored 3 papers about 3 hours ago

updated a collection about 9 hours ago

OpenSAE Infrastructure & Evaluation

Collection

Reproducible tools and evidence for sparse autoencoder research • 2 items • Updated about 9 hours ago

Hunter26666666

updated 2 Spaces about 9 hours ago

OpenSAE

🧱

Open research for testable explanations of neural networks.

SAEBase Research Lab

🧱

Explore verified SAE checkpoints, interventions and results.

Hunter26666666

published a Space about 9 hours ago

SAEBase Research Lab

🧱

Explore verified SAE checkpoints, interventions and results.

Hunter26666666

updated a dataset about 9 hours ago

OpenSAE/SAEBase-Evaluation

Viewer • Updated about 9 hours ago • 240 • 23 • 1

Hunter26666666

published a dataset about 9 hours ago

OpenSAE/SAEBase-Evaluation

Viewer • Updated about 9 hours ago • 240 • 23 • 1

Hunter26666666

updated a collection about 10 hours ago

SAE Benchmarks, Datasets & Models

Collection

Benchmarks, datasets, and pretrained models for reproducible sparse autoencoder research, feature interventions, and mechanistic interpretability. • 10 items • Updated about 10 hours ago • 1

AI & ML interests

Recent Activity

Papers

Team members 1

OpenSAE's activity

OpenSAE

SAEBase Research Lab

SAEBase Research Lab