quantified-uncertainty / ai-safety-papers
☆20Updated 3 years ago
Related projects: ⓘ
- Mechanistic Interpretability for Transformer Models☆48Updated 2 years ago
- A dataset of alignment research and code to reproduce it☆68Updated last year
- 📚📚📚📚📚📚📚📚📚 Reading everything☆12Updated 4 months ago
- ☆10Updated last year
- ☆18Updated last year
- ☆33Updated 3 months ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆169Updated 2 years ago
- we got you bro☆32Updated last month
- Tools for studying developmental interpretability in neural networks.☆69Updated this week
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆88Updated 2 years ago
- Language-annotated Abstraction and Reasoning Corpus☆76Updated last year
- Sparse Autoencoder Training Library☆18Updated last month
- Redwood Research's transformer interpretability tools☆11Updated 2 years ago
- This repo is built to facilitate the training and analysis of autoregressive transformers on maze-solving tasks.☆24Updated 3 weeks ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆182Updated this week
- ☆24Updated 5 months ago
- Image augmentation library for Jax☆36Updated 5 months ago
- ☆12Updated 3 years ago
- See the issue board for the current status of active and prospective projects!☆65Updated 2 years ago
- Interpreting how transformers simulate agents performing RL tasks☆62Updated 10 months ago
- 🧠 Starter templates for doing interpretability research☆59Updated last year
- (Model-written) LLM evals library☆14Updated last month
- The Happy Faces Benchmark☆14Updated last year
- Python Research Framework☆107Updated last year
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆13Updated 5 months ago
- Documentation for dynamic machine learning systems.☆26Updated last week
- Code for reproducing the results from the paper Avoiding Side Effects in Complex Environments☆12Updated 3 years ago
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆58Updated 2 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆57Updated 10 months ago
- A programming language for formal/informal computation.☆39Updated 3 months ago