curt-tigges / crosslayer-codingLinks
☆13Updated last week
Alternatives and similar repositories for crosslayer-coding
Users that are interested in crosslayer-coding are comparing it to the libraries listed below
Sorting:
- ☆15Updated 3 months ago
- Unified access to Large Language Model modules using NNsight☆21Updated this week
- Modified to support crosscoder training.☆20Updated 2 weeks ago
- Mechanistic Interpretability Visualizations using React☆262Updated 7 months ago
- ☆47Updated 8 months ago
- ☆123Updated last year
- ☆231Updated 9 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆193Updated this week
- ☆182Updated 3 months ago
- ☆107Updated this week
- Engine for collecting, uploading, and downloading model activations☆20Updated 3 months ago
- Sparse Autoencoder Training Library☆53Updated 2 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆206Updated 7 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆608Updated last week
- A tiny easily hackable implementation of a feature dashboard.☆12Updated 2 weeks ago
- ☆315Updated this week
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Updated 9 months ago
- ☆146Updated 8 months ago
- A library for efficient patching and automatic circuit discovery.☆70Updated 2 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 8 months ago
- ☆79Updated 4 months ago
- ☆32Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 6 months ago
- ☆121Updated 11 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆256Updated 11 months ago
- (Model-written) LLM evals library☆18Updated 7 months ago
- Attribution-based Parameter Decomposition☆27Updated last month
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- ☆60Updated this week
- ☆100Updated 5 months ago