elhage-2022-publication-authors

IN premise — summaries/2026/08/24/elhage-2022-toy-models-superposition-chunk-2.md

Created 2026-08-25T02:57:58+00:00

The paper 'Toy Models of Superposition' was authored by Nelson Elhage, Catherine Olsson, Robert Lasenby, et al. at Anthropic and Harvard, published September 14, 2022.

Summary

This pins down the provenance of the "Toy Models of Superposition" paper: a small group at Anthropic and Harvard, led by Nelson Elhage, produced it in September 2022. It matters because any downstream reasoning that cites or builds on that work needs a reliable, checkable anchor for who is responsible for the ideas and when they entered the public record.