csinva / interpretable-embeddings
Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)
☆37Updated 5 months ago
Alternatives and similar repositories for interpretable-embeddings:
Users that are interested in interpretable-embeddings are comparing it to the libraries listed below
- ☆22Updated 2 months ago
- maze datasets for investigating OOD behavior of ML systems☆41Updated 2 weeks ago
- Universal Neurons in GPT2 Language Models☆27Updated 10 months ago
- ☆91Updated 2 months ago
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆120Updated 7 months ago
- ☆90Updated 9 months ago
- ☆83Updated last year
- ☆50Updated 2 weeks ago
- Code and data for the paper "Understanding Hidden Context in Preference Learning: Consequences for RLHF"☆29Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆162Updated last week
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆47Updated 2 months ago
- Exploring the Limitations of Large Language Models on Multi-Hop Queries☆25Updated last month
- ☆93Updated last year
- ☆90Updated 2 months ago
- [arXiv] EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees☆17Updated last month
- ☆14Updated 2 months ago
- A library for efficient patching and automatic circuit discovery.☆63Updated this week
- The Prism Alignment Project☆75Updated last year
- ☆104Updated 5 months ago
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆105Updated last year
- ☆26Updated last year
- ☆62Updated 2 years ago
- ☆34Updated last year
- ☆30Updated 5 months ago
- ☆114Updated 8 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆52Updated 5 months ago
- Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"☆151Updated 5 months ago
- ☆96Updated 9 months ago
- ☆40Updated last year
- ☆26Updated 8 months ago