curt-tigges / crosslayer-codingLinks
☆16Updated 6 months ago
Alternatives and similar repositories for crosslayer-coding
Users that are interested in crosslayer-coding are comparing it to the libraries listed below
Sorting:
- Modified to support crosscoder training.☆25Updated 3 weeks ago
- ☆20Updated 9 months ago
- ☆30Updated this week
- ☆58Updated last year
- Unified access to Large Language Model modules using NNsight☆87Updated last week
- ☆36Updated last year
- ☆267Updated last year
- ☆83Updated 11 months ago
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆55Updated this week
- A library for efficient patching and automatic circuit discovery.☆88Updated last month
- Mechanistic Interpretability Visualizations using React☆318Updated last year
- ☆132Updated 2 years ago
- ☆206Updated 3 months ago
- Sparse Autoencoder Training Library☆56Updated 9 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆238Updated last year
- ☆143Updated last month
- ☆81Updated last week
- ☆388Updated 5 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆241Updated last week
- ☆137Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆45Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Updated last year
- ☆197Updated last year
- Engine for collecting, uploading, and downloading model activations☆25Updated 10 months ago
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Updated last year
- How do transformer LMs encode relations?☆55Updated last year
- Sparse Autoencoder for Mechanistic Interpretability☆290Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆800Updated this week
- Attribution-based Parameter Decomposition☆33Updated 7 months ago