# Switched linear projections for neural network interpretability

arXiv: https://arxiv.org/abs/1909.11275 · HTML: https://mlsanity.com/paper/1909.11275/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2019.

## Built on by (most cited first, 1 of 1)

- [Conceptual capacity and effective complexity of neural networks](https://mlsanity.com/paper/2103.07614/) (2021)

## Abstract (arXiv)

We introduce switched linear projections for expressing the activity of a neuron in a deep neural network in terms of a single linear projection in the input space. The method works by isolating the active subnetwork, a series of linear transformations, that determine the entire computation of the network for a given input instance. With these projections we can decompose activity in any hidden layer into patterns detected in a given input instance. We also propose that in ReLU networks it is instructive and meaningful to examine patterns that deactivate the neurons in a hidden layer, something that is implicitly ignored by the existing interpretability methods tracking solely the active aspect of the network's computation.