These failure cases are particularly troubling because they are not systematic; it is very difficult to predict when, for example, the order of information seemingly randomly causes a model to fail [Pezeshkpour and Hruschka, 2023, Liu et al., 2024, Li and Gao, 2024, Zheng et al.,

These failure cases are particularly troubling because they are not systematic; it is very difficult to predict when, for example, the order of information seemingly randomly causes a model to fail [Pezeshkpour and Hruschka, 2023, Liu et al., 2024, Li and Gao, 2024, Zheng et al.,

The process of meaning composition, wherein smaller units like morphemes or words combine to form the meaning of phrases and sentences, is essential for human sentence comprehension. Despite extensive neurolinguistic research into the brain regions involved in meaning composition, a computational metric to quantify the extent of composition is still lacking. Drawing on the key-value memory interpretation of transformer feed-forward network blocks, we introduce the Composition Score, a novel model-based metric designed to quantify the degree of meaning composition during sentence comprehension. Experimental findings show that this metric correlates with brain clusters associated with word frequency, structural processing, and general sensitivity to words, suggesting the multifaceted nature of meaning composition during human sentence comprehension.

Although it is known that transformer language models (LMs) pass features from early layers to later layers, it is not well understood how this information is represented and routed by the model. By analyzing particular mechanism LMs use to accomplish this, we find that it is also used to recall items from a list, and show that this mechanism can explain an otherwise arbitrary-seeming sensitivity of the model to the order of items in the prompt. Specifically, we find that models write into low-rank subspaces of the residual stream to represent features which are then read out by specific later layers, forming low-rank communication channels between layers. By decomposing attention head weight matrices with the Singular Value Decomposition (SVD), we find that previously described interactions between heads separated by one or more layers can be predicted via analysis of their weight matrices. We show that it is possible to manipulate the internal model representations as well as edit model weights based on the mechanism we discover in order to significantly improve performance on our synthetic Laundry List task, which requires recall from a list, often improving task accuracy by over 20%. Our analysis reveals a surprisingly intricate interpretable structure learned from language model pretraining, and helps us understand why sophisticated LMs sometimes fail in simple domains, facilitating future analysis of more complex behaviors.