Interpretability & Safety · 2021

A Mathematical Framework for Transformer Circuits

Nelson Elhage, Neel Nanda, Catherine Olsson, Tom Henighan, Chris Olah

Provided a mathematical account of attention-only Transformers as compositions of interpretable operations, making the attention mechanism analyzable rather than opaque.

Editorial record

Plain-language summary

The report decomposes a Transformer into a residual stream that attention heads read from and write to, and shows how heads compose across layers to move and combine information. It introduces tools like the QK and OV circuits and identifies simple mechanisms in small models. This gave mechanistic interpretability a concrete framework for studying language models.

Knowledge graph

Relationships

Antecedents

Descendants

Source record

Provenance

Record ID
P-501
Record created
2026-07-13
Last reviewed
2026-07-14
Record version
2

Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.