EffiSciencesResearch / ML4GLinks
Machine Learning for Alignment Bootcamp
☆25Updated last year
Alternatives and similar repositories for ML4G
Users that are interested in ML4G are comparing it to the libraries listed below
Sorting:
- Tools for studying developmental interpretability in neural networks.☆94Updated 5 months ago
- Machine Learning for Alignment Bootcamp☆74Updated 3 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆207Updated 2 weeks ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆216Updated last year
- ControlArena is a suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alp…☆69Updated this week
- Mechanistic Interpretability Visualizations using React☆257Updated 6 months ago
- ☆19Updated 2 years ago
- we got you bro☆35Updated 10 months ago
- A dataset of alignment research and code to reproduce it☆77Updated 2 years ago
- ☆55Updated 9 months ago
- 🧠 Starter templates for doing interpretability research☆71Updated last year
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆127Updated 2 years ago
- METR Task Standard☆151Updated 4 months ago
- ☆227Updated 8 months ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆96Updated this week
- ☆82Updated 11 months ago
- A curated list of awesome resources for Artificial Intelligence Alignment research☆71Updated last year
- Erasing concepts from neural representations with provable guarantees☆228Updated 5 months ago
- ☆98Updated 3 months ago
- ☆26Updated 2 years ago
- Machine Learning for Alignment Bootcamp (MLAB).☆30Updated 3 years ago
- (Model-written) LLM evals library☆18Updated 6 months ago
- ☆121Updated last year
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆14Updated last year
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆108Updated last year
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago
- ☆280Updated 11 months ago
- ☆11Updated 11 months ago
- ☆270Updated last year