Xmaster6y / lczerolens
π¬ Interpretability for Leela Chess Zero networks.
β12Updated this week
Alternatives and similar repositories for lczerolens:
Users that are interested in lczerolens are comparing it to the libraries listed below
- Code for "Evidence of Learned Look-Ahead in a Chess-Playing Neural Network"β20Updated 10 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)β18Updated 3 months ago
- π§ Starter templates for doing interpretability researchβ70Updated last year
- Sparse Autoencoder Training Libraryβ48Updated 5 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"β73Updated 5 months ago
- β22Updated 2 months ago
- β12Updated 2 weeks ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from eβ¦β26Updated 11 months ago
- A library for efficient patching and automatic circuit discovery.β63Updated this week
- β128Updated 3 weeks ago
- β37Updated 2 months ago
- β71Updated 2 months ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizationsβ14Updated last year
- β11Updated last month
- Arrakis is a library to conduct, track and visualize mechanistic interpretability experiments.β28Updated this week
- A small package implementing some useful wrapping around nnsightβ12Updated last week
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden Stateβ18Updated last year
- Erasing concepts from neural representations with provable guaranteesβ227Updated 3 months ago
- Applying SAEs for fine-grained controlβ17Updated 4 months ago
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entityβ¦β25Updated last year
- β54Updated 7 months ago
- Experiments for efforts to train a new and improved t5β77Updated last year
- β16Updated 5 months ago
- A library for mechanistic anomaly detectionβ21Updated 3 months ago
- https://footprints.baulab.infoβ17Updated 6 months ago
- A set of Python scripts that makes your experience on TPU betterβ51Updated 9 months ago
- Steering vectors for transformer language models in Pytorch / Huggingfaceβ95Updated 2 months ago
- Redwood Research's transformer interpretability toolsβ14Updated 3 years ago
- β80Updated 9 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"β69Updated 10 months ago