amack315 / unsupervised-steering-vectors
☆24Updated 6 months ago
Related projects ⓘ
Alternatives and complementary repositories for unsupervised-steering-vectors
- ☆44Updated this week
- ☆107Updated this week
- Steering vectors for transformer language models in Pytorch / Huggingface☆65Updated last month
- ☆105Updated last month
- Sparse Autoencoder Training Library☆27Updated 3 weeks ago
- Steering Llama 2 with Contrastive Activation Addition☆98Updated 5 months ago
- Tools for studying developmental interpretability in neural networks.☆77Updated last week
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆78Updated last year
- Measuring the situational awareness of language models☆33Updated 9 months ago
- ☆108Updated last year
- A library for efficient patching and automatic circuit discovery.☆31Updated last month
- Mechanistic Interpretability Visualizations using React☆200Updated 4 months ago
- ☆188Updated last month
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆123Updated last month
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆157Updated last month
- ☆24Updated 7 months ago
- ☆10Updated 4 months ago
- ☆145Updated 3 weeks ago
- METR Task Standard☆124Updated 3 weeks ago
- ☆101Updated 3 months ago
- ☆28Updated last month
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆25Updated 5 months ago
- Improving Alignment and Robustness with Circuit Breakers☆154Updated last month
- Experiments with representation engineering☆10Updated 8 months ago
- ☆20Updated last week
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆61Updated last week
- ☆98Updated 3 months ago
- ☆44Updated last month
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆62Updated 5 months ago
- (Model-written) LLM evals library☆16Updated 3 months ago