TransformerLensOrg / CircuitsVis
Mechanistic Interpretability Visualizations using React
☆195Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for CircuitsVis
- ☆186Updated last month
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆157Updated last month
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆399Updated this week
- Training Sparse Autoencoders on Language Models☆449Updated this week
- ☆102Updated last month
- Using sparse coding to find distributed representations used by neural networks.☆181Updated 11 months ago
- ☆108Updated last year
- ☆141Updated 2 weeks ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆194Updated 9 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆187Updated 3 months ago
- ☆96Updated 3 months ago
- Sparse autoencoders☆333Updated 2 weeks ago
- Steering Llama 2 with Contrastive Activation Addition☆94Updated 5 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆64Updated last month
- ☆99Updated this week
- Tools for understanding how transformer predictions are built layer-by-layer☆429Updated 5 months ago
- Tools for studying developmental interpretability in neural networks.☆74Updated this week
- ☆252Updated 8 months ago
- ☆43Updated 4 months ago
- Mechanistic Interpretability for Transformer Models☆49Updated 2 years ago
- Erasing concepts from neural representations with provable guarantees☆208Updated 3 weeks ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆186Updated this week
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆95Updated 2 years ago
- ☆168Updated 8 months ago
- This repository collects all relevant resources about interpretability in LLMs☆282Updated last week
- ☆337Updated this week
- A library for efficient patching and automatic circuit discovery.☆30Updated last month
- Extract full next-token probabilities via language model APIs☆228Updated 8 months ago
- Sparse probing paper full code.☆50Updated 10 months ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆168Updated last year