UlisseMini / procgen-tools
Tools for running experiments on RL agents in procgen environments
☆16Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for procgen-tools
- ☆19Updated last year
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆194Updated 9 months ago
- Machine Learning for Alignment Bootcamp☆63Updated 2 years ago
- Machine Learning for Alignment Bootcamp (MLAB).☆22Updated 2 years ago
- Tools for studying developmental interpretability in neural networks.☆74Updated this week
- ☆18Updated last year
- (Model-written) LLM evals library☆16Updated 3 months ago
- ☆24Updated 7 months ago
- Mechanistic Interpretability Visualizations using React☆195Updated 3 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆186Updated this week
- Machine Learning for Alignment Bootcamp☆25Updated 8 months ago
- ☆44Updated last month
- My writings about ARC (Abstraction and Reasoning Corpus)☆57Updated this week
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆95Updated 2 years ago
- ☆186Updated last month
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆13Updated 6 months ago
- ☆12Updated last year
- METR Task Standard☆122Updated last week
- 🧠 Starter templates for doing interpretability research☆63Updated last year
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆62Updated this week
- ☆10Updated 3 months ago
- ☆96Updated 3 months ago
- ☆23Updated 6 months ago
- Learning Universal Predictors☆69Updated 3 months ago
- Code for 1st place solution to Kaggle's Abstraction and Reasoning Challenge☆143Updated 4 years ago
- A text-based game where language models learn to lie and to detect lies.☆11Updated last year
- Algebraic value editing in pretrained language models☆57Updated last year
- Redwood Research's transformer interpretability tools☆12Updated 2 years ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆168Updated last year
- Draw more samples☆174Updated 4 months ago