safety-research / safety-examplesLinks
☆15Updated this week
Alternatives and similar repositories for safety-examples
Users that are interested in safety-examples are comparing it to the libraries listed below
Sorting:
- Inference API for many LLMs and other useful tools for empirical research☆49Updated last week
- ControlArena is a suite of realistic settings, mimicking complex deployment environments, for running control evaluations. This is an alp…☆69Updated this week
- METR Task Standard☆151Updated 4 months ago
- ☆11Updated 11 months ago
- (Model-written) LLM evals library☆18Updated 6 months ago
- Machine Learning for Alignment Bootcamp☆74Updated 3 years ago
- Redwood Research's transformer interpretability tools☆14Updated 3 years ago
- A python sdk for LLM finetuning and inference on runpod infrastructure☆11Updated last week
- Repository with sample code using Apollo's suggested engineering practices☆9Updated 6 months ago
- Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.☆216Updated last year
- Tools for studying developmental interpretability in neural networks.☆95Updated this week
- Mechanistic Interpretability Visualizations using React☆258Updated 6 months ago
- ☆31Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆21Updated 7 months ago
- ☆66Updated last month
- A TinyStories LM with SAEs and transcoders☆11Updated 2 months ago
- ☆13Updated 2 months ago
- ☆28Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 8 months ago
- ☆44Updated 7 months ago
- Decoder only transformer, built from scratch with PyTorch☆30Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆127Updated 2 years ago
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago
- ☆227Updated 8 months ago
- Modified to support crosscoder training.☆17Updated this week
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆35Updated last year
- A small package implementing some useful wrapping around nnsight☆13Updated this week
- Experiments with representation engineering☆11Updated last year
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆96Updated this week
- Interpreting how transformers simulate agents performing RL tasks☆84Updated last year