curt-tigges / crosslayer-codingLinks
☆15Updated last month
Alternatives and similar repositories for crosslayer-coding
Users that are interested in crosslayer-coding are comparing it to the libraries listed below
Sorting:
- ☆15Updated 4 months ago
- Unified access to Large Language Model modules using NNsight☆44Updated last week
- Modified to support crosscoder training.☆22Updated last month
- Mechanistic Interpretability Visualizations using React☆281Updated 8 months ago
- A tiny easily hackable implementation of a feature dashboard.☆12Updated last month
- ☆81Updated 6 months ago
- ☆53Updated 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 …☆207Updated last week
- Engine for collecting, uploading, and downloading model activations☆22Updated 4 months ago
- ☆116Updated last month
- ☆33Updated last year
- ☆238Updated 11 months ago
- ☆335Updated last week
- Sparse Autoencoder Training Library☆54Updated 4 months ago
- Applying SAEs for fine-grained control☆23Updated 8 months ago
- ☆184Updated last month
- ☆126Updated last year
- Inference API for many LLMs and other useful tools for empirical research☆68Updated 2 weeks ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆214Updated 8 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆638Updated last week
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆19Updated 7 months ago
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- ☆21Updated 3 weeks ago
- ☆122Updated last year
- Attribution-based Parameter Decomposition☆29Updated 2 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆58Updated 10 months ago
- ☆163Updated 9 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆260Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- Sparse probing paper full code.☆59Updated last year