UlisseMini / procgen-tools
Tools for running experiments on RL agents in procgen environments
☆16Updated 9 months ago
Alternatives and similar repositories for procgen-tools:
Users that are interested in procgen-tools are comparing it to the libraries listed below
- Machine Learning for Alignment Bootcamp (MLAB).☆24Updated 3 years ago
- Tools for studying developmental interpretability in neural networks.☆83Updated last week
- ☆18Updated 2 years ago
- ☆19Updated last year
- (Model-written) LLM evals library☆17Updated last month
- Machine Learning for Alignment Bootcamp☆70Updated 2 years ago
- ☆10Updated 6 months ago
- ☆12Updated last year
- we got you bro☆34Updated 6 months ago
- Interpreting how transformers simulate agents performing RL tasks☆77Updated last year
- ☆25Updated 9 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆14Updated 2 months ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆77Updated this week
- ☆49Updated 4 months ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆209Updated 11 months ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆14Updated 9 months ago
- ☆61Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated last week
- The AI that helps you achieve your goals☆11Updated 11 months ago
- Resources from the EleutherAI Math Reading Group☆52Updated last month
- My writings about ARC (Abstraction and Reasoning Corpus)☆64Updated 3 weeks ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆193Updated this week
- Machine Learning for Alignment Bootcamp☆25Updated 10 months ago
- Redwood Research's transformer interpretability tools☆13Updated 2 years ago
- This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.☆26Updated 5 months ago
- ☆55Updated this week
- ☆82Updated 3 weeks ago
- Mechanistic Interpretability for Transformer Models☆49Updated 2 years ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆70Updated 2 years ago
- 🧠 Starter templates for doing interpretability research☆65Updated last year