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
2
3
The Biology of a Large Language Model
We investigate the internal mechanisms used by Claude 3.5 Haiku — Anthropic's lightweight production model — in a variety of contexts, using our circuit tracing methodology.
4
A Mathematical Framework for Transformer Circuits (2021)
Transformer language models are an emerging technology that is gaining increasingly broad real-world use, for example in systems like GPT-3 , LaMDA , Codex , Meena , Gopher , and similar models. However, as these models scale, their open-endedness and high capacity creates an increasing scope for unexpected and…
5