EleutherAI / sparsifyLinks
Sparsify transformers with SAEs and transcoders
☆608Updated this week
Alternatives and similar repositories for sparsify
Users that are interested in sparsify are comparing it to the libraries listed below
Sorting:
- Training Sparse Autoencoders on Language Models☆919Updated this week
- ☆327Updated this week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆211Updated 8 months ago
- ☆508Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆630Updated this week
- Sparse Autoencoder for Mechanistic Interpretability☆258Updated last year
- Mechanistic Interpretability Visualizations using React☆280Updated 8 months ago
- Using sparse coding to find distributed representations used by neural networks.☆262Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆206Updated this week
- ☆237Updated 10 months ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆793Updated 2 weeks ago
- Tools for understanding how transformer predictions are built layer-by-layer☆514Updated 2 weeks ago
- ☆111Updated last month
- ☆184Updated last month
- ☆52Updated 9 months ago
- ☆126Updated last year
- ☆162Updated 9 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆197Updated 9 months ago
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆297Updated last month
- This repository collects all relevant resources about interpretability in LLMs☆368Updated 9 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆221Updated last week
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆257Updated 2 months ago
- Steering Llama 2 with Contrastive Activation Addition☆174Updated last year
- Decoder only transformer, built from scratch with PyTorch☆31Updated last year
- ☆185Updated 9 months ago
- ☆138Updated 4 months ago
- ☆276Updated last year
- Modified to support crosscoder training.☆21Updated 3 weeks ago
- Open source interpretability artefacts for R1.☆157Updated 4 months ago