quantified-uncertainty / ai-safety-papersLinks
☆22Updated 4 years ago
Alternatives and similar repositories for ai-safety-papers
Users that are interested in ai-safety-papers are comparing it to the libraries listed below
Sorting:
- A dataset of alignment research and code to reproduce it☆78Updated 2 years ago
- Tools for studying developmental interpretability in neural networks.☆111Updated 4 months ago
- The Happy Faces Benchmark☆15Updated 2 years ago
- Mechanistic Interpretability for Transformer Models☆53Updated 3 years ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆198Updated 3 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆211Updated this week
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆14Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago
- ☆65Updated 2 years ago
- ☆16Updated 3 weeks ago
- A TinyStories LM with SAEs and transcoders☆13Updated 6 months ago
- ☆19Updated 2 years ago
- ☆84Updated last year
- ☆29Updated last year
- METR Task Standard☆163Updated 8 months ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆191Updated 2 years ago
- Machine Learning for Alignment Bootcamp☆79Updated 3 years ago
- AI Safety Q&A web frontend☆41Updated last week
- gpt completions in vscode☆35Updated 2 years ago
- ☆305Updated last year
- (Model-written) LLM evals library☆18Updated 10 months ago
- A programming language for formal/informal computation.☆41Updated 2 months ago
- ☆19Updated this week
- Language-annotated Abstraction and Reasoning Corpus☆93Updated 2 years ago
- Einsum with einops style variable names☆17Updated last year
- 🧠 Starter templates for doing interpretability research☆74Updated 2 years ago
- ☆19Updated last year
- ☆138Updated 3 months ago
- Measuring the situational awareness of language models☆38Updated last year