Computational Superposition in a Toy Model of the U-AND Problem — LessWrong

Thanks to @Linda Linsefors and @Kola Ayonrinde for reviewing the draft. …

x Computational Superposition in a Toy Model of the U-AND Problem — LessWrong Interpretability (ML & AI) Superposition AI Frontpage 18 Computational Superposition in a Toy Model of the U-AND Problem by Adam Newgas 27th Mar 2025 14 min read 2 18 Thanks to @Linda Linsefors and @Kola Ayonrinde for reviewing the draft. tl;dr: I built a toy model of the Universal-AND Problem described in Toward A Mathematical Framework for Computation in Superposition (CiS). It successfully learnt a solution to the problem, providing evidence that such computational superposition [1] can occur in the wild. In this

related reading

• Toy Models of Superpositiontransformer-circuits.pub
• Circuits in Superposition 2: Now with Less Wrong Math — LessWronglesswrong.com
• Zoom In: An Introduction to Circuitsdistill.pub
• Ping pong computation in superposition — LessWronglesswrong.com
• Interpretability Dreamstransformer-circuits.pub
• Weight-Sparse Circuits May Be Interpretable Yet Unfaithful — LessWronglesswrong.com
• Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
• Circuits Updates — May 2023transformer-circuits.pub
• What Would Non-Linear Features Actually Look Like? — Liv Gortonlivgorton.com
• Toward A Mathematical Framework for Computation in Superposition — LessWronglesswrong.com
• Language Model Circuits Are Sparse in the Neuron Basis | Transluce AItransluce.org
• Circuits Updates - January 2024transformer-circuits.pub