TransformerLensOrg / CircuitsVisLinks
Mechanistic Interpretability Visualizations using React
☆302Updated 11 months ago
Alternatives and similar repositories for CircuitsVis
Users that are interested in CircuitsVis are comparing it to the libraries listed below
Sorting:
- ☆255Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆228Updated 11 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆707Updated this week
- ☆132Updated 2 years ago
- ☆367Updated 3 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆284Updated last year
- Sparsify transformers with SAEs and transcoders☆665Updated this week
- ☆189Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆286Updated 2 years ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆232Updated 3 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆228Updated this week
- ☆196Updated last month
- Tools for understanding how transformer predictions are built layer-by-layer☆549Updated 3 months ago
- ☆136Updated 2 weeks ago
- ☆130Updated last year
- Training Sparse Autoencoders on Language Models☆1,075Updated last week
- ☆57Updated last year
- ☆283Updated last year
- Unified access to Large Language Model modules using NNsight☆60Updated last week
- Steering vectors for transformer language models in Pytorch / Huggingface☆130Updated 9 months ago
- Tools for studying developmental interpretability in neural networks.☆116Updated 5 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆216Updated last year
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆132Updated this week
- METR Task Standard☆168Updated 9 months ago
- ☆83Updated 9 months ago
- Attribution-based Parameter Decomposition☆32Updated 5 months ago
- Steering Llama 2 with Contrastive Activation Addition☆195Updated last year
- Decoder only transformer, built from scratch with PyTorch☆31Updated 2 years ago
- ☆549Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆62Updated last year