redwoodresearch / mlabLinks
Machine Learning for Alignment Bootcamp
☆76Updated 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.☆220Updated last year
- Machine Learning for Alignment Bootcamp (MLAB).☆30Updated 3 years ago
- METR Task Standard☆156Updated 6 months ago
- Mechanistic Interpretability Visualizations using React☆272Updated 7 months ago
- Tools for studying developmental interpretability in neural networks.☆100Updated last month
- (Model-written) LLM evals library☆18Updated 7 months ago
- Inference API for many LLMs and other useful tools for empirical research☆61Updated this week
- ☆646Updated last week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆622Updated last week
- 🧠 Starter templates for doing interpretability research☆73Updated 2 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated last week
- ControlArena is a collection of settings, model organisms and protocols - for running control experiments.☆80Updated last week
- ☆234Updated 10 months ago
- ☆99Updated 4 months ago
- ☆19Updated last month
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆194Updated 3 years ago
- ☆124Updated last year
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago
- we got you bro☆36Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- ☆287Updated last year
- ☆18Updated 2 years ago
- ☆63Updated 2 years ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆103Updated last week
- Decoder only transformer, built from scratch with PyTorch☆31Updated last year
- A python sdk for LLM finetuning and inference on runpod infrastructure☆12Updated this week
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆128Updated 2 years ago
- ☆55Updated last week
- Repository with sample code using Apollo's suggested engineering practices☆11Updated 7 months ago
- ☆274Updated last year