Xmaster6y / lczerolensLinks
π¬ Interpretability for Leela Chess Zero networks.
β13Updated 2 weeks ago
Alternatives and similar repositories for lczerolens
Users that are interested in lczerolens are comparing it to the libraries listed below
Sorting:
- Code for "Evidence of Learned Look-Ahead in a Chess-Playing Neural Network"β22Updated last year
- A small package implementing some useful wrapping around nnsightβ13Updated this week
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementingβ¦β10Updated 8 months ago
- Redwood Research's transformer interpretability toolsβ15Updated 3 years ago
- β12Updated last month
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)β18Updated 4 months ago
- Mechanistic Interpretability for Transformer Modelsβ51Updated 3 years ago
- A library for efficient patching and automatic circuit discovery.β65Updated last month
- β19Updated 2 years ago
- Sparse Autoencoder Training Libraryβ52Updated last month
- Applying SAEs for fine-grained controlβ18Updated 5 months ago
- β31Updated last year
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden Stateβ18Updated last year
- Attribution-based Parameter Decompositionβ24Updated this week
- Tools for studying developmental interpretability in neural networks.β91Updated 4 months ago
- β82Updated 11 months ago
- β75Updated 3 months ago
- β50Updated last month
- Engine for collecting, uploading, and downloading model activationsβ18Updated 2 months ago
- Erasing concepts from neural representations with provable guaranteesβ228Updated 4 months ago
- Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.β29Updated last month
- Mechanistic Interpretability Visualizations using Reactβ253Updated 5 months ago
- β28Updated last year
- Modified to support crosscoder training.β17Updated this week
- METR Task Standardβ148Updated 4 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"β34Updated last year
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entityβ¦β26Updated last year
- π§ Starter templates for doing interpretability researchβ69Updated last year
- (Model-written) LLM evals libraryβ18Updated 5 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from eβ¦β27Updated last year