Transformer based AI models such as Large Language Models (LLMs) have demonstrated remarkable performance in a number of different tasks. Even though these models are typically trained to predict only the next token/sequence, transformer models seem to have an ability to generalise to a wider range of tasks. Understanding how transformer models achieve such capabilities it is an active area of research in the AI Safety space i.e. Mechanistic Interpretability.

In this article I will explain what are 'Transformer's Induction Heads', the intuition behind these and I will describe how to visualize attention heads using libraries such as TransformerLens and CircuitsViz, and how to identify induction heads — a special type of attention heads. For an indepth introduction to Induction Heads and the broader topic of Mechanistic Interpretability, I recommend the [ARENA](https://mango-ambulance-93a.notion.site/ARENA-Virtual-Resources-7934b3cbcfbf4f249acac8842f887a99) course as well as the article [In-context Learning and Induction Heads](https://transformer-circuits.pub/2022/in-context-learning-and-induction-heads/index.html) and [A Mathematical Framework for Transformer Circuits](https://transformer-circuits.pub/2021/framework/index.html#induction-heads).

> Read the full piece [here](https://medium.com/@natisie/understanding-transformers-induction-heads-bf379bcb4715).


Understanding Transformer's Induction Heads

Natalia Burton • Top submission • July 2024