understanding-search / maze-transformerLinks
This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.
☆30Updated 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:
- see github.com/understanding-search/maze-transformer☆10Updated last year
- Interpreting how transformers simulate agents performing RL tasks☆84Updated last year
- ☆26Updated 2 years ago
- Tools for studying developmental interpretability in neural networks.☆94Updated 5 months ago
- maze datasets for investigating OOD behavior of ML systems☆48Updated 3 weeks ago
- Sparse Autoencoder Training Library☆52Updated last month
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago
- Minimal but scalable implementation of large language models in JAX☆35Updated 7 months ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆78Updated 2 years ago
- Scaling scaling laws with board games.☆49Updated last year
- Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery☆16Updated last year
- Code for the paper "Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making"☆27Updated 11 months ago
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆87Updated 3 months ago
- A collection of meta-learning algorithms in Jax☆23Updated 2 years ago
- we got you bro☆35Updated 10 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆20Updated 7 months ago
- Universal Neurons in GPT2 Language Models☆29Updated last year
- Code for Discovered Policy Optimisation (NeurIPS 2022)☆11Updated 2 years ago
- ☆51Updated last year
- Official Implementation of `An Optimisation Framework for Unsupervised Environment Design` from RLC 2025☆11Updated 3 weeks ago
- ☆12Updated 11 months ago
- Code for "Evidence of Learned Look-Ahead in a Chess-Playing Neural Network"☆24Updated last year
- Attribution-based Parameter Decomposition☆25Updated 2 weeks ago
- ☆29Updated 3 months ago
- ☆28Updated last year
- ☆67Updated 2 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 5 months ago
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago
- MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research☆21Updated last week
- Comparison between GFlowNets & Maximum Entropy RL☆18Updated last year