sae
flexsae
Official Triton kernels for TopK and HierarchicalTopK Sparse Autoencoder decoders.
- 29
- Python
- Apache-2.0
- 14 mo ago
AutoEncoders-TensorFlow2
🚢 Simple implementations of various popular Deep Reinforcement Learning algorithms using TensorFlow2
- 6
- Python
- Apache-2.0
- 7 y ago
LouvreSAE
Official Implementation of 'LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfer'
- 5
- Jupyter Notebook
- 11 mo ago
qwen-scope-lab
Inspect, steer & monitor a real LLM on Apple Silicon — a browser-based SAE interpretability lab for Qwen Scope, powered by MLX
- 4
- Python
- Apache-2.0
- 3 mo ago
AbsTopK-SAE
[ICLR 2026] AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features
- 3
- Python
- MIT
- 5 mo ago
Recommender-System
We use stacked Autoencoders to build a powerfull recommender system for movies.
- 2
- Python
- GPL-3.0
- 5 y ago
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-10-hook_mlp_out-l1-1e-05
Feature extraction model, used with torch.
- 0
- 49
- apache-2.0
- 17 mo ago
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-11-hook_resid_post-l1-1e-05
Feature extraction model, used with torch.
- 0
- 40
- apache-2.0
- 19 mo ago
sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-11-hook_mlp_out-l1-5e-05
Feature extraction model, used with torch.
- 0
- 30
- apache-2.0
- 2 y ago
synth-sae-bench-16k-v1-saes
- 0
- 1.2k
- mit
- 6 mo ago