# Dissecting Pruned Neural Networks

arXiv: https://arxiv.org/abs/1907.00262 · HTML: https://mlsanity.com/paper/1907.00262/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2019.

## Built on by (most cited first, 8 of 8)

- [Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks](https://mlsanity.com/paper/2207.13243/) (2022)
- [Break It Down: Evidence for Structural Compositionality in Neural Networks](https://mlsanity.com/paper/2301.10884/) (2023)
- [Concept-Monitor: Understanding DNN training through individual neurons](https://mlsanity.com/paper/2304.13346/) (2023)
- [Exploring the Lottery Ticket Hypothesis with Explainability Methods: Insights into Sparse Network Performance](https://mlsanity.com/paper/2307.13698/) (2023)
- [Investigating the Effect of Network Pruning on Performance and Interpretability](https://mlsanity.com/paper/2409.19727/) (2024)
- [Do Sparse Subnetworks Exhibit Cognitively Aligned Attention? Effects of Pruning on Saliency Map Fidelity, Sparsity, and Concept Coherence](https://mlsanity.com/paper/2509.21387/) (2025)
- [Insights into the Lottery Ticket Hypothesis and Iterative Magnitude Pruning](https://mlsanity.com/paper/2403.15022/) (2024)
- [Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliability in Medical Imaging](https://mlsanity.com/paper/2609.07803/) (2026)

## Abstract (arXiv)

Pruning is a standard technique for removing unnecessary structure from a neural network to reduce its storage footprint, computational demands, or energy consumption. Pruning can reduce the parameter-counts of many state-of-the-art neural networks by an order of magnitude without compromising accuracy, meaning these networks contain a vast amount of unnecessary structure. In this paper, we study the relationship between pruning and interpretability. Namely, we consider the effect of removing unnecessary structure on the number of hidden units that learn disentangled representations of human-recognizable concepts as identified by network dissection. We aim to evaluate how the interpretability of pruned neural networks changes as they are compressed. We find that pruning has no detrimental effect on this measure of interpretability until so few parameters remain that accuracy beings to drop. Resnet-50 models trained on ImageNet maintain the same number of interpretable concepts and units until more than 90% of parameters have been pruned.