etredal / openCLTLinks
☆56Updated 2 months ago
Alternatives and similar repositories for openCLT
Users that are interested in openCLT are comparing it to the libraries listed below
Sorting:
- Using sparse coding to find distributed representations used by neural networks.☆289Updated 2 years ago
- ☆191Updated last year
- ☆552Updated last year
- Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.☆168Updated this week
- ☆366Updated 3 months ago
- ☆223Updated last year
- ☆136Updated 3 weeks ago
- Sparse Autoencoder for Mechanistic Interpretability☆285Updated last year
- ☆195Updated 2 months ago
- This repository collects all relevant resources about interpretability in LLMs☆387Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆231Updated last week
- A resource repository for representation engineering in large language models☆143Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆196Updated last year
- ☆240Updated last year
- ☆58Updated last year
- Modified to support crosscoder training.☆24Updated 2 months ago
- A curated reading list of research in Sparse Autoencoders, Feature Extraction and related topics in Mechanistic Interpretability☆30Updated 10 months ago
- ☆259Updated last year
- Sparsify transformers with SAEs and transcoders☆672Updated last week
- A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..☆286Updated 8 months ago
- [NeurIPS D&B '25] The one-stop repository for large language model (LLM) unlearning. Supports TOFU, MUSE, WMDP, and many unlearning metho…☆444Updated last week
- Training Sparse Autoencoders on Language Models☆1,104Updated 2 weeks ago
- ☆242Updated last year
- FeatureAlignment = Alignment + Mechanistic Interpretability☆33Updated 9 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆232Updated 11 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆311Updated 6 months ago
- ☆111Updated 10 months ago
- ☆132Updated 2 years ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆166Updated 7 months ago
- awesome SAE papers☆66Updated 6 months ago