English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Two Heads, One Path: How a Minimal Transformer 'Sees' Logic — A Deep Dive into the Minimal IOI Circuit

Forum topic · 小凯 · 2026-05-06

Summary

A detailed explainer of the paper 'Emergence of Minimal Circuits for Indirect Object Identification in Attention-Only Transformers' (arXiv:2510.25013) by Rabin Adhikari (Saarland University). The paper trains a stripped-down Transformer—one layer, two attention heads, no MLP, no LayerNorm—to solve the Indirect Object Identification (IOI) task in a symbolic, template-based setting, achieving 100% accuracy. Spectral analysis reveals a clean division of labor: Head 0 acts as an 'adder' that copies both candidate answers (sum direction), while Head 1 acts as a 'contrastor' that suppresses the wrong one (difference direction). In the residual stream, the incorrect-copy terms cancel and the correct answer is amplified, showing that error cancellation is a learned solution rather than a designed one. Ablations show a single head performs at chance (~50%), two single-head layers reach only ~86%, and removing positional encoding drops accuracy to ~70%, indicating position information is integral to the logical structure. The post frames the work as a proof of principle for mechanistic interpretability: multi-head specialization and emergent minimal circuits can be studied precisely in toy models, with caveats that the 100% result applies only to the symbolic task and that minimality claims depend on the architecture and training search space.

A detailed explainer of the paper 'Emergence of Minimal Circuits for Indirect Object Identification in Attention-Only Transformers' (arXiv:2510.25013) by Rabin Adhikari (Saarland University). The paper trains a stripped-down Transformer—one layer, two attention heads, no MLP, no LayerNorm—to solve the Indirect Object Identification (IOI) task in a symbolic, template-based setting, achieving 100% accuracy. Spectral analysis reveals a clean division of labor: Head 0 acts as an 'adder' that copies both candidate answers (sum direction), while Head 1 acts as a 'contrastor' that suppresses the wrong one (difference direction). In the residual stream, the incorrect-copy terms cancel and the correct answer is amplified, showing that error cancellation is a learned solution rather than a designed one. Ablations show a single head performs at chance (~50%), two single-head layers reach only ~86%, and removing positional encoding drops accuracy to ~70%, indicating position information is integral to the logical structure. The post frames the work as a proof of principle for mechanistic interpretability: multi-head specialization and emergent minimal circuits can be studied precisely in toy models, with caveats that the 100% result applies only to the symbolic task and that minimality claims depend on the architecture and training search space.

Tags

#mechanistic-interpretability#transformer#attention-heads#indirect-object-identification#minimal-circuits#residual-stream#arxiv-2510-25013

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177619538