redwoodresearch / mlabLinks
Machine Learning for Alignment Bootcamp
☆78Updated 3 years ago
Alternatives and similar repositories for mlab
Users that are interested in mlab are comparing it to the libraries listed below
Sorting:
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆223Updated 2 weeks ago
- Machine Learning for Alignment Bootcamp (MLAB).☆30Updated 3 years ago
- Tools for studying developmental interpretability in neural networks.☆101Updated 2 months ago
- Mechanistic Interpretability Visualizations using React☆281Updated 8 months ago
- METR Task Standard☆159Updated 6 months ago
- (Model-written) LLM evals library☆18Updated 8 months ago
- ☆676Updated last week
- 🧠 Starter templates for doing interpretability research☆73Updated 2 years ago
- ☆238Updated 10 months ago
- Inference API for many LLMs and other useful tools for empirical research☆68Updated last week
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆88Updated this week
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated this week
- ☆20Updated 2 months ago
- ☆18Updated 2 years ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆638Updated this week
- we got you bro☆36Updated last year
- ☆291Updated last year
- ☆101Updated 5 months ago
- ☆126Updated last year
- ☆63Updated 2 years ago
- Machine Learning for Alignment Bootcamp☆26Updated last year
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago
- ☆29Updated last year
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆195Updated 3 years ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆214Updated 8 months ago
- Tools for running experiments on RL agents in procgen environments☆19Updated last year
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆108Updated last week
- Draw more samples☆193Updated last year
- ☆56Updated 3 weeks ago
- Extract full next-token probabilities via language model APIs☆247Updated last year