yash-srivastava19 / arrakisLinks
Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.
☆31Updated 5 months ago
Alternatives and similar repositories for arrakis
Users that are interested in arrakis are comparing it to the libraries listed below
Sorting:
- Attribution-based Parameter Decomposition☆31Updated 4 months ago
- Engine for collecting, uploading, and downloading model activations☆24Updated 6 months ago
- ☆142Updated last month
- ☆81Updated 7 months ago
- Open source interpretability artefacts for R1.☆161Updated 5 months ago
- 🧠 Starter templates for doing interpretability research☆75Updated 2 years ago
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆221Updated 10 months ago
- ☆29Updated last year
- Mechanistic Interpretability Visualizations using React☆291Updated 10 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- code for training & evaluating Contextual Document Embedding models☆197Updated 5 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 7 months ago
- we got you bro☆36Updated last year
- ☆73Updated last week
- Extract full next-token probabilities via language model APIs☆247Updated last year
- An introduction to LLM Sampling☆79Updated 10 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆216Updated last week
- Experiments with representation engineering☆13Updated last year
- Training-Ready RL Environments + Evals☆128Updated this week
- ☆109Updated 8 months ago
- PyTorch library for Active Fine-Tuning☆93Updated 3 weeks ago
- ☆128Updated last year
- ☆50Updated 3 weeks ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- A library for efficient patching and automatic circuit discovery.☆77Updated 2 months ago
- A tiny easily hackable implementation of a feature dashboard.☆15Updated last month
- Prune transformer layers☆69Updated last year
- nanoGPT-like codebase for LLM training☆107Updated 5 months ago