← Latest products

GPT Circuits

Mapping the inner workings of simple LLMs. View interpretable “circuits” extracted from LLMs using the GPT-2 architecture. I've built an app that extracts interpretable 'circuits' from models using the GPT-2 architecture.

Visit peterlai.github.ioexternal site

Reactions (1)

Similar products

by description similarity

  1. prove program to LLM circuit equivalence

    Hacker News16 pts

  2. dreamGPT

    github.com

    What if LLM hallucinations were a feature and not a bug?

    Hacker News34 pts

  3. NanoEuler

    github.com

    GPT-2 scale model in pure C/CUDA from scratch

    Hacker News55 pts

  4. ZigFormer

    news.ycombinator.com

    An LLM implemented in pure Zig

    Hacker News22 pts

  5. A behavioural health monitor for LLMs

    Hacker News10 pts