understanding-search / maze-transformerLinks
This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.
☆29Updated 9 months ago
Alternatives and similar repositories for maze-transformer
Users that are interested in maze-transformer are comparing it to the libraries listed below
Sorting:
- Interpreting how transformers simulate agents performing RL tasks☆82Updated last year
- see github.com/understanding-search/maze-transformer☆10Updated last year
- maze datasets for investigating OOD behavior of ML systems☆46Updated last week
- Code for "Evidence of Learned Look-Ahead in a Chess-Playing Neural Network"☆22Updated last year
- ☆26Updated 2 years ago
- ☆13Updated 10 months ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆78Updated 2 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 4 months ago
- Code for the paper "Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making"☆27Updated 10 months ago
- Scaling scaling laws with board games.☆49Updated last year
- Code for experiments on transformers using Markovian data.☆14Updated 6 months ago
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆14Updated 7 months ago
- An Open-Ended Agentic Simulator☆51Updated 9 months ago
- POPGym Library in JAX☆11Updated last year
- Official Implementation of `An Optimisation Framework for Unsupervised Environment Design` from RLC 2025☆11Updated last week
- ☆23Updated 4 months ago
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆84Updated 2 months ago
- A small package implementing some useful wrapping around nnsight☆13Updated last month
- Tools for studying developmental interpretability in neural networks.☆91Updated 4 months ago
- Redwood Research's transformer interpretability tools☆15Updated 3 years ago
- Sparse Autoencoder Training Library☆52Updated last month
- ☆37Updated 8 months ago
- Universal Neurons in GPT2 Language Models☆29Updated last year
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- ☆19Updated 2 years ago
- Code for Discovered Policy Optimisation (NeurIPS 2022)☆10Updated last year
- Official codebase for "Sampling For Learnability", published at NeurIPS 2024☆15Updated this week
- Scalable Opponent Shaping Experiments in JAX☆24Updated last year
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- ☆28Updated last year