mukobi / welfare-diplomacy
General-Sum variant of the game Diplomacy for evaluating AIs.
☆23Updated 7 months ago
Related projects ⓘ
Alternatives and complementary repositories for welfare-diplomacy
- ☆122Updated last week
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆83Updated 7 months ago
- Algebraic value editing in pretrained language models☆57Updated last year
- Mechanistic Interpretability for Transformer Models☆49Updated 2 years ago
- Redwood Research's transformer interpretability tools☆12Updated 2 years ago
- Interpreting how transformers simulate agents performing RL tasks☆69Updated last year
- Code and data for the paper "Understanding Hidden Context in Preference Learning: Consequences for RLHF"☆26Updated 10 months ago
- Sparse Autoencoder Training Library☆26Updated 2 weeks ago
- Rewarded soups official implementation☆50Updated last year
- Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)☆21Updated 5 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆78Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆26Updated 5 months ago
- ☆32Updated last year
- ☆18Updated last month
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆62Updated last year
- A library for efficient patching and automatic circuit discovery.☆30Updated last month
- Steering vectors for transformer language models in Pytorch / Huggingface☆64Updated last month
- Jiminy Cricket Environment (NeurIPS 2021)☆24Updated 2 years ago
- ☆24Updated 7 months ago
- Experiments with representation engineering☆10Updated 8 months ago
- ☆102Updated last month
- ☆187Updated last month
- ☆44Updated last month
- ☆12Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆61Updated 4 months ago
- Measuring the situational awareness of language models☆33Updated 9 months ago
- ☆96Updated 3 months ago
- ☆70Updated 3 months ago
- Steering Llama 2 with Contrastive Activation Addition☆95Updated 5 months ago
- 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