kutay25 / ai-safety-alignment-camps
An repository of 2025-2026 AI Safety and Alignment programs, camps, and workshops.
☆21Updated this week
Alternatives and similar repositories for ai-safety-alignment-camps:
Users that are interested in ai-safety-alignment-camps are comparing it to the libraries listed below
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆210Updated last year
- ☆71Updated 2 months ago
- ☆519Updated this week
- Mechanistic Interpretability Visualizations using React☆241Updated 4 months ago
- Machine Learning for Alignment Bootcamp (MLAB).☆29Updated 3 years ago
- Tools for studying developmental interpretability in neural networks.☆89Updated 3 months ago
- small language models training made easy☆13Updated 4 months ago
- 🧠 Starter templates for doing interpretability research☆70Updated last year
- ☆12Updated 2 weeks ago
- ☆274Updated 2 months ago
- we got you bro☆35Updated 8 months ago
- Attribution-based Parameter Decomposition☆18Updated this week
- ☆219Updated 6 months ago
- (Model-written) LLM evals library☆18Updated 4 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆169Updated this week
- ☆121Updated last year
- Machine Learning for Alignment Bootcamp☆72Updated 3 years ago
- A benchmark for mechanistic discovery of circuits in Transformers☆13Updated 4 months ago
- ☆37Updated 5 months ago
- Repository with sample code using Apollo's suggested engineering practices☆8Updated 4 months ago
- ☆49Updated 3 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆52Updated 6 months ago
- ☆91Updated 2 weeks ago
- METR Task Standard☆146Updated 2 months ago
- ☆10Updated 9 months ago
- Sparsify transformers with SAEs and transcoders☆520Updated this week
- Sparse Autoencoder for Mechanistic Interpretability☆241Updated 9 months ago
- TransformerLens + HuggingFace☆11Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆548Updated this week
- Using sparse coding to find distributed representations used by neural networks.☆236Updated last year