yash-srivastava19 / arrakisLinks
Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.
☆31Updated 7 months ago
Alternatives and similar repositories for arrakis
Users that are interested in arrakis are comparing it to the libraries listed below
Sorting:
- Engine for collecting, uploading, and downloading model activations☆24Updated 8 months ago
- Attribution-based Parameter Decomposition☆33Updated 6 months ago
- ☆144Updated 3 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆232Updated last year
- 🧠 Starter templates for doing interpretability research☆74Updated 2 years ago
- This was designed for interp researchers who want to do research on or with interp agents to give quality of life improvements and fix …☆48Updated this week
- Sparse Autoencoder Training Library☆55Updated 7 months ago
- ☆83Updated 9 months ago
- Course Materials for Interpretability of Large Language Models (0368.4264) at Tel Aviv University☆227Updated 3 weeks ago
- Unified access to Large Language Model modules using NNsight☆70Updated last month
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆231Updated last week
- ☆132Updated 2 years ago
- we got you bro☆36Updated last year
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆20Updated last month
- Utilities for the HuggingFace transformers library☆72Updated 2 years ago
- A library for efficient patching and automatic circuit discovery.☆82Updated 4 months ago
- Mechanistic Interpretability Visualizations using React☆304Updated last year
- Extract full next-token probabilities via language model APIs☆248Updated last year
- Erasing concepts from neural representations with provable guarantees☆239Updated 10 months ago
- A tiny easily hackable implementation of a feature dashboard.☆15Updated 2 months ago
- code for training & evaluating Contextual Document Embedding models☆201Updated 7 months ago
- Open source interpretability artefacts for R1.☆165Updated 7 months ago
- PyTorch library for Active Fine-Tuning☆95Updated 2 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Updated last year
- ☆36Updated last year
- ☆29Updated 5 months 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
- ☆112Updated 10 months ago
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆51Updated last year