evandez / relations
How do transformer LMs encode relations?
☆37Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for relations
- A library for efficient patching and automatic circuit discovery.☆30Updated last month
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆85Updated 3 years ago
- ☆70Updated 3 months ago
- ☆79Updated last year
- ☆102Updated last month
- ☆96Updated 3 months ago
- Sparse probing paper full code.☆50Updated 10 months ago
- Algebraic value editing in pretrained language models☆57Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆118Updated last month
- ☆186Updated last month
- Sparse Autoencoder Training Library☆26Updated 2 weeks ago
- Inspecting and Editing Knowledge Representations in Language Models☆107Updated last year
- ☆74Updated last month
- ☆168Updated 8 months ago
- Steering Llama 2 with Contrastive Activation Addition☆95Updated 5 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆64Updated last month
- A toolkit for describing model features and intervening on those features to steer behavior.☆74Updated this week
- ☆75Updated 9 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆77Updated last year
- ☆94Updated 6 months ago
- ☆105Updated this week
- ☆43Updated 4 months ago
- AI Logging for Interpretability and Explainability🔬☆87Updated 5 months ago
- ☆108Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆52Updated last week
- 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
- ☆28Updated 7 months ago
- Using sparse coding to find distributed representations used by neural networks.☆181Updated last year
- ☆68Updated 3 months ago
- ☆58Updated last year