# What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation

arXiv: https://arxiv.org/abs/2404.07129 · HTML: https://mlsanity.com/paper/2404.07129/

## Key facts

- Cited by 89 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Apr 2024.

## Built on by (most cited first, 30 of 89)

- [A Primer on the Inner Workings of Transformer-based Language Models](https://mlsanity.com/paper/2405.00208/) (2024)
- [Attention Heads of Large Language Models: A Survey](https://mlsanity.com/paper/2409.03752/) (2024)
- [LLM Circuit Analyses Are Consistent Across Training and Scale](https://mlsanity.com/paper/2407.10827/) (2024)
- [Training Dynamics of In-Context Learning in Linear Attention](https://mlsanity.com/paper/2501.16265/) (2025)
- [Talking Heads: Understanding Inter-layer Communication in Transformer Language Models](https://mlsanity.com/paper/2406.09519/) (2024)
- [Out-of-distribution generalization via composition: a lens through induction heads in Transformers](https://mlsanity.com/paper/2408.09503/) (2024)
- [The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling](https://mlsanity.com/paper/2410.09223/) (2024)
- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [Optimal ablation for interpretability](https://mlsanity.com/paper/2409.09951/) (2024)
- [The emergence of sparse attention: impact of data distribution and benefits of repetition](https://mlsanity.com/paper/2505.17863/) (2025)
- [Can In-context Learning Really Generalize to Out-of-distribution Tasks?](https://mlsanity.com/paper/2410.09695/) (2024)
- [Toward Understanding In-context vs. In-weight Learning](https://mlsanity.com/paper/2410.23042/) (2024)
- [Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context Learning](https://mlsanity.com/paper/2505.17097/) (2025)
- [Revisiting In-context Learning Inference Circuit in Large Language Models](https://mlsanity.com/paper/2410.04468/) (2024)
- [Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts](https://mlsanity.com/paper/2410.10626/) (2024)
- [Strategy Coopetition Explains the Emergence and Transience of In-Context Learning](https://mlsanity.com/paper/2503.05631/) (2025)
- [Linking In-context Learning in Transformers to Human Episodic Memory](https://mlsanity.com/paper/2405.14992/) (2024)
- [Does learning the right latent variables necessarily improve in-context learning?](https://mlsanity.com/paper/2405.19162/) (2024)
- [Transformer Dynamics: A neuroscientific approach to interpretability of large language models](https://mlsanity.com/paper/2502.12131/) (2025)
- [Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence](https://mlsanity.com/paper/2505.16694/) (2025)
- [Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning](https://mlsanity.com/paper/2505.18752/) (2025)
- [Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs](https://mlsanity.com/paper/2512.08417/) (2025)
- [Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units](https://mlsanity.com/paper/2601.21996/) (2026)
- [Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention](https://mlsanity.com/paper/2605.29548/) (2026)
- [Mechanistic evaluation of Transformers and state space models](https://mlsanity.com/paper/2505.15105/) (2025)
- [Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models](https://mlsanity.com/paper/2509.17588/) (2025)
- [Understanding In-context Learning of Addition via Activation Subspaces](https://mlsanity.com/paper/2505.05145/) (2025)
- [Context Structure Reshapes the Representational Geometry of Language Models](https://mlsanity.com/paper/2601.22364/) (2026)
- [Survival of the Fittest Representation: A Case Study with Modular Addition](https://mlsanity.com/paper/2405.17420/) (2024)
- [ELICIT: LLM Augmentation via External In-Context Capability](https://mlsanity.com/paper/2410.09343/) (2024)

## Abstract (arXiv)

In-context learning is a powerful emergent ability in transformer models. Prior work in mechanistic interpretability has identified a circuit element that may be critical for in-context learning -- the induction head (IH), which performs a match-and-copy operation. During training of large transformers on natural language data, IHs emerge around the same time as a notable phase change in the loss. Despite the robust evidence for IHs and this interesting coincidence with the phase change, relatively little is known about the diversity and emergence dynamics of IHs. Why is there more than one IH, and how are they dependent on each other? Why do IHs appear all of a sudden, and what are the subcircuits that enable them to emerge? We answer these questions by studying IH emergence dynamics in a controlled setting by training on synthetic data. In doing so, we develop and share a novel optogenetics-inspired causal framework for modifying activations throughout training. Using this framework, we delineate the diverse and additive nature of IHs. By clamping subsets of activations throughout training, we then identify three underlying subcircuits that interact to drive IH formation, yielding the phase change. Furthermore, these subcircuits shed light on data-dependent properties of formation, such as phase change timing, already showing the promise of this more in-depth understanding of subcircuits that need to "go right" for an induction head.