quantified-uncertainty / ai-safety-papersLinks
☆21Updated 3 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☆77Updated last year
- Mechanistic Interpretability for Transformer Models☆51Updated 3 years ago
- Redwood Research's transformer interpretability tools☆15Updated 3 years ago
- The Happy Faces Benchmark☆15Updated last year
- we got you bro☆35Updated 10 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆204Updated last week
- ☆19Updated 2 years ago
- Tools for studying developmental interpretability in neural networks.☆91Updated 4 months ago
- Language-annotated Abstraction and Reasoning Corpus☆86Updated 2 years ago
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆189Updated 3 years ago
- ☆63Updated 2 years ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆126Updated 2 years ago
- ☆9Updated 9 months ago
- gpt completions in vscode☆34Updated 2 years ago
- ☆14Updated this week
- ☆26Updated 2 years ago
- 📚 📚📚📚📚📚📚📚📚 Reading everything☆14Updated last month
- My writings about ARC (Abstraction and Reasoning Corpus)☆78Updated last week
- Interpreting how transformers simulate agents performing RL tasks☆82Updated last year
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆78Updated 2 years ago
- Machine Learning for Alignment Bootcamp☆73Updated 3 years ago
- Implementing RASP transformer programming language https://arxiv.org/pdf/2106.06981.pdf.☆53Updated 3 years ago
- See the issue board for the current status of active and prospective projects!☆65Updated 3 years ago
- ☆28Updated last year
- Experiments with representation engineering☆11Updated last year
- Python Research Framework☆106Updated 2 years ago
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆12Updated 2 years ago
- An environment for learning formal mathematical reasoning from scratch☆67Updated 9 months ago
- ☆9Updated 5 years ago
- A curated list of awesome resources for Artificial Intelligence Alignment research☆70Updated last year