Satvik Golechha

Satvik Golechha, Dylan Cope, Nandi Schoots

An approach to improve network interpretability is via clusterability, i.e., splitting a model into disjoint clusters that can be studied independently. We find pretrained models to be highly unclusterable and thus train models to be more modular using an ``enmeshment loss'' function that encourages the formation of non-interacting clusters. Using automated interpretability measures, we show that our method finds clusters that learn different, disjoint, and smaller circuits for CIFAR-10 labels. Our approach provides a promising direction for making neural networks easier to interpret.

Satvik Golechha, Maheep Chaudhary, Joan Velja et al.

An approach to improve neural network interpretability is via clusterability, i.e., splitting a model into disjoint clusters that can be studied independently. We define a measure for clusterability and show that pre-trained models form highly enmeshed clusters via spectral graph clustering. We thus train models to be more modular using a "clusterability loss" function that encourages the formation of non-interacting clusters. We then investigate the emerging properties of these highly clustered models. We find our trained clustered models do not exhibit more task specialization, but do form smaller circuits. We investigate CNNs trained on MNIST and CIFAR, small transformers trained on modular addition, and GPT-2 and Pythia on the Wiki dataset, and Gemma on a Chemistry dataset. This investigation shows what to expect from clustered models.