TransformerLensOrg / CircuitsVisLinks
Mechanistic Interpretability Visualizations using React
☆251Updated 5 months ago
Alternatives and similar repositories for CircuitsVis
Users that are interested in CircuitsVis are comparing it to the libraries listed below
Sorting:
- ☆222Updated 7 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆200Updated 5 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆248Updated 10 months ago
- Using sparse coding to find distributed representations used by neural networks.☆247Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆574Updated this week
- ☆121Updated last year
- ☆302Updated last week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆180Updated this week
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆213Updated last year
- Tools for studying developmental interpretability in neural networks.☆90Updated 4 months ago
- Sparsify transformers with SAEs and transcoders☆547Updated this week
- ☆120Updated 6 months ago
- ☆96Updated last month
- ☆116Updated 9 months ago
- Training Sparse Autoencoders on Language Models☆789Updated this week
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆125Updated 2 years ago
- ☆170Updated last month
- Tools for understanding how transformer predictions are built layer-by-layer☆493Updated 11 months ago
- This repository collects all relevant resources about interpretability in LLMs☆353Updated 6 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆101Updated 3 months ago
- ☆74Updated 3 months ago
- 🧠 Starter templates for doing interpretability research☆70Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- ☆42Updated 6 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆204Updated this week
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- Extract full next-token probabilities via language model APIs☆248Updated last year
- A toolkit for describing model features and intervening on those features to steer behavior.☆184Updated 6 months ago
- Attribution-based Parameter Decomposition☆21Updated last week
- Erasing concepts from neural representations with provable guarantees☆227Updated 4 months ago