Xmaster6y / lczerolensLinks
š¬ Interpretability for Leela Chess Zero networks.
ā14Updated last month
Alternatives and similar repositories for lczerolens
Users that are interested in lczerolens are comparing it to the libraries listed below
Sorting:
- we got you broā35Updated 10 months ago
- Code for "Evidence of Learned Look-Ahead in a Chess-Playing Neural Network"ā24Updated last year
- ā28Updated last year
- Mechanistic Interpretability for Transformer Modelsā51Updated 3 years ago
- Sparse Autoencoder Training Libraryā52Updated last month
- The Happy Faces Benchmarkā15Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)ā18Updated 5 months ago
- A library for efficient patching and automatic circuit discovery.ā67Updated 2 months ago
- ā55Updated 9 months ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden Stateā18Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from eā¦ā27Updated last year
- š§ Starter templates for doing interpretability researchā71Updated last year
- Attribution-based Parameter Decompositionā25Updated 2 weeks ago
- Utilities for the HuggingFace transformers libraryā68Updated 2 years ago
- ā19Updated 2 years ago
- Redwood Research's transformer interpretability toolsā14Updated 3 years ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"ā75Updated 7 months ago
- ā99Updated 4 months ago
- Tools for studying developmental interpretability in neural networks.ā95Updated this week
- Multiple datasets for ARC (Abstraction and Reasoning Corpus)ā70Updated 3 months ago
- Algebraic value editing in pretrained language modelsā65Updated last year
- A collection of different ways to implement accessing and modifying internal model activations for LLMsā18Updated 8 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"ā35Updated last year
- ā35Updated 2 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.ā207Updated 2 weeks ago
- ā134Updated 7 months ago
- Experiments with representation engineeringā11Updated last year
- Erasing concepts from neural representations with provable guaranteesā228Updated 5 months ago
- ā26Updated 2 years ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizationsā14Updated last year