Get the latest tech news
Mapping the Mind of a Large Language Model
We have identified how millions of concepts are represented inside Claude Sonnet, one of our deployed large language models. This is the first ever detailed look inside a modern, production-grade large language model.
In October 2023, we reported success applying dictionary learning to a very small "toy" language model and found coherent features corresponding to concepts like uppercase text, DNA sequences, surnames in citations, nouns in mathematics, or function arguments in Python code. We see features corresponding to a vast range of entities like cities (San Francisco), people (Rosalind Franklin), atomic elements (Lithium), scientific fields (immunology), and programming syntax (function calls). The orange color denotes the words or word-parts on which the feature is active.We also find more abstract features—responding to things like bugs in computer code, discussions of gender bias in professions, and conversations about keeping secrets.
Or read this on Hacker News
