Gabriel Franco

Entity tracking (ET), the ability to keep track of states, is a fundamental skill that underlies complex reasoning. An increasing amount of work investigates how transformer language models (LMs) solve entity binding without state changes. However, there is limited understanding of how non-toy LMs address ET problems of realistic difficulties expressed in natural language. To this end, we investigate the mechanisms underlying ET in more complex scenarios featuring multiple state-changing operations. We find that LMs do not incrementally track world states across tokens or query-relevant states across layers, but simply aggregate relevant information in parallel at the last token when the query becomes evident.

Identifying feature representations in language models is a central task in mechanistic interpretability. Several recent studies have made the observation that feature representations can be inferred in some cases from singular vectors of attention matrices. However, sound justification for this phenomenon is lacking. In this paper we address that question, asking: why and when do singular vectors align with features? First, we demonstrate that singular vectors robustly align with features in a model where features can be directly observed. We then show theoretically that such alignment is expected under a range of conditions. We close by asking how, operationally, alignment may be recognized in real models where feature representations are not directly observable.

Understanding the internal circuits that language models use to solve tasks remains a central challenge in mechanistic interpretability. A crucial part of finding circuits is understanding why each attention head attends where it does. To this end, we introduce ACC++, an improved circuit-tracing method based on the principle of attention-causal communication (ACC), which identifies signals, i.e., contents of low dimensional subspaces that cause attention on a token pair. ACC++ extracts circuits from a single forward pass, without replacement models or patching. Circuits identified by ACC++ consist of components that are causal for the model’s attention decisions, together with the low-dimensional signals used to communicate between them.

The attention mechanism plays a central role in the computations performed by transformer-based models, and understanding the reasons why heads attend to specific tokens can aid in interpretability of language models. Although considerable work has shown that models construct low-dimensional feature representations, little work has explicitly tied low-dimensional features to the attention mechanism itself. In this paper we work to bridge this gap by presenting methods for identifying attention-causal communication, meaning low-dimensional features that are written into and read from tokens, and that have a provable causal relationship to attention patterns. We show that by identifying those signals, we can perform prompt-specific circuit discovery in a single forward pass. Further, we show that signals can uncover unexplored mechanisms at work in the model, including a surprising degree of global coordination across attention heads.