TransformerLensOrg / CircuitsVisLinks
Mechanistic Interpretability Visualizations using React
☆303Updated last year
Alternatives and similar repositories for CircuitsVis
Users that are interested in CircuitsVis are comparing it to the libraries listed below
Sorting:
- ☆260Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆232Updated last year
- ☆132Updated 2 years ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆738Updated this week
- ☆370Updated 4 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆286Updated last year
- Sparsify transformers with SAEs and transcoders☆673Updated last week
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆234Updated 4 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆234Updated last week
- ☆136Updated last month
- ☆196Updated 2 months ago
- Using sparse coding to find distributed representations used by neural networks.☆289Updated 2 years ago
- Tools for understanding how transformer predictions are built layer-by-layer☆554Updated 4 months ago
- ☆192Updated last year
- Unified access to Large Language Model modules using NNsight☆70Updated last month
- ☆58Updated last year
- Training Sparse Autoencoders on Language Models☆1,118Updated this week
- ☆83Updated 9 months ago
- ☆134Updated last year
- Tools for studying developmental interpretability in neural networks.☆117Updated 5 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆223Updated last week
- ☆283Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆131Updated 3 years ago
- 🧠 Starter templates for doing interpretability research☆74Updated 2 years ago
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆135Updated last week
- Steering vectors for transformer language models in Pytorch / Huggingface☆134Updated 10 months ago
- Steering Llama 2 with Contrastive Activation Addition☆201Updated last year
- ☆19Updated 8 months ago
- Attribution-based Parameter Decomposition☆33Updated 6 months ago
- This repository collects all relevant resources about interpretability in LLMs☆389Updated last year