SAELens inference works with any PyTorch-based model, not just TransformerLens. While we provide deep integration with TransformerLens via HookedSAETransformer, SAEs can be used with Hugging Face Transformers, NNsight, or any other framework by extracting activations and passing them to the SAE's encode() and decode() methods.
Unclaimed
Are you the maintainer?
Claim this page →Saelens
Training Sparse Autoencoders on Language Models
A 87/100 GitHub score ? This grade is derived from GitHub signals, not user votes. Open for the full
breakdown.
Discussion 01 / Summary
About Saelens.
02 / Discussion CREDIBILITY-GATED
Discussion
Reading is open to everyone. Posting and voting need a verified identity or a GitHub grade of B or higher.
- No discussions yet.
03 / Related
More around Saelens.
Similar tools
Deepspeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Diffusers
Library of pretrained diffusion models for generating images, audio, and 3D structures, for inference or training
Wandb
Tracks and visualizes machine learning experiments and models, with framework integrations and cloud or self-hosted deployment
Rf Detr
A real-time transformer architecture for object detection, instance segmentation, and keypoint detection (preview) developed by Roboflow.
04 / Build
Build with Saelens.
Browse the catalog for frameworks, tools, and harnesses, each scored on real GitHub credibility.
Get Saelens →