Papers for

ai interpretability engineers

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Training vision transformers with spatial loss improves causal circuit grouping

Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity

Abstract: Mechanistic interpretability of vision transformers seeks to decompose model computation into human-readable units, but learned representations entangle many concepts in each neuron. Feature superposition is widely treated as the central obstacle to this decomposition, yet most mitigations (sparse autoencoders, dictionary learning) are post-hoc and leave the underlying network unchanged. We ask whether a spatial-locality training loss (TopoLoss) can act as a lightweight, training-time prior that improves interpretability of standard mech-interp tools. Training ViT on ImageNet-100 across multiple TopoLoss weights $α$, we measure causal sufficiency of topographic clusters via activation patching and feature geometry via sparse autoencoders fit to the same residual stream. At $α=1.0$, topographic clusters are 2.79$\times$ more causally sufficient than random unit sets of the same size, with the effect increasing monotonically in $α$. SAE L0 sparsity decreases by 11% and dead-feature fraction rises 19-fold, yet standard neuron-level monosemanticity scores are unchanged, indicating that topographic pressure acts at circuit level, concentrating causal mass into spatially local structures without disentangling individual neurons. This dissociation suggests current neuron-level monosemanticity metrics are insensitive to a class of real interpretability gains, and positions cheap architectural priors as a viable training-time complement to post-hoc tooling.

Mon 21 SeptComputer Vision and Pattern RecognitionMachine Learning
The gist
Vision transformer models often mix many ideas within single neurons, making them hard to interpret. The authors tried a new training method called TopoLoss that encourages neurons near each other to work on related parts of the task. They found this makes groups of neurons more meaningful and causally effective together, but individual neurons still represent mixed concepts. This shows that looking at individual neurons may miss important patterns in how the model works.
Open 2609.24379v1