Topics
Results for “mechanistic interpretability”
4 results
- Tools for exploring the souls of large language models — Hacker News · Seen · 52 points
- Sparks of Weight-Space Programming: LLMs can natively read & write neural network weights — 2 sources · Seen · 2,935 points
- AI torture chamber: deep dive into whether model can feel pain — DEV Community · Seen
- How Vision Transformers Represent Position: A Mechanistic Comparison of Absolute and Rotary Positional Encodings — arXiv AI Papers · Seen