Ping pong computation in superposition — LessWrong

Overview: This post builds on Circuits in Superposition 2, using the same terminology. …

x Ping pong computation in superposition — LessWrong Comp-In-Sup Interpretability (ML & AI) Superposition AI Frontpage 13 Ping pong computation in superposition by Alex Gibson 29th Dec 2025 4 min read 0 13 Overview: This post builds on Circuits in Superposition 2 , using the same terminology. I focus on the z = 1 case, meaning that exactly one circuit is active on each forward pass. This restriction simplifies the setting substantially and allows a construction with zero error, with T = D 2 d 2 , L + 2 layers, and width D ( 1 + 1 d + ⌈ log 2 D d ⌉ D ) . While the construction does not directly

saved by

• Asher P

related reading

• Investigating the learning coefficient of modular addition: hackathon project — LessWronglesswrong.com
• AlgZoo: uninterpreted models with fewer than 1,500 parameters — LessWronglesswrong.com
• Circuits in Superposition 2: Now with Less Wrong Math — LessWronglesswrong.com
• Toy Models of Superpositiontransformer-circuits.pub
• Computational Superposition in a Toy Model of the U-AND Problem — LessWronglesswrong.com
• Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
• Zoom In: An Introduction to Circuitsdistill.pub
• Toward A Mathematical Framework for Computation in Superposition — LessWronglesswrong.com
• Reverse Engineering a Neural Network's Clever Solution to Binary Addition - Casey Primozic's Homepagecprimozic.net
• Neural networks and deep learningneuralnetworksanddeeplearning.com
• Interpretability Dreamstransformer-circuits.pub
• Superposition, Memorization, and Double Descenttransformer-circuits.pub