1
Circuit Tracing: Revealing Computational Graphs in Language Models (Anthropic)
We describe an approach to tracing the “step-by-step” computation involved when a model responds to a single prompt.
Transformer Circuits
Can we reverse engineer transformer language models into human-understandable computer programs?
- Popular posts
- 5
- Total points
- 565
- HN comments
- 187
- Rank
- #2,430 company
Visit transformer-circuits.pub → RSS feedOn Hacker News Oct 2022 – Sep 2026
AI & Machine Learning 5Software Engineering 3Science & Space 1Math & Algorithms 1