How does GPT-2 Predict Acronyms? Extracting and Understanding a Circuit via Mechanistic Interpretability

Transformer-based language models are treated as black-boxes because of their large number of parameters and complex internal interactions, which is a serious safety concern. Mechanistic Interpretability (MI) intends to reverse-engineer neural network behaviors in terms of human-understandable components. In this work, we focus on understanding how GPT-2 Small performs the task of predicting three-letter acronyms. Previous works in the MI field have focused so far on tasks that predict a single token. To the best of our knowledge, this is the first work that tries to mechanistically understand a behavior involving the prediction of multiple consecutive tokens. We discover that the prediction is performed by a circuit composed of 8 attention heads (${\sim}5\%$ of the total heads) which we classified in three groups according to their role. We also demonstrate that these heads concentrate the acronym prediction functionality. In addition, we mechanistically interpret the most relevant heads of the circuit and find out that they use positional information which is propagated via the causal mask mechanism. We expect this work to lay the foundation for understanding more complex behaviors involving multiple-token predictions.