# Identifying Information-Transfer Nodes in a Recurrent Neural Network Reveals Dynamic Representations

arXiv: https://arxiv.org/abs/2510.01271 · HTML: https://mlsanity.com/paper/2510.01271/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 28 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models](https://mlsanity.com/paper/1708.08296/) (2017)
- [The structure of evolved representations across different substrates for artificial intelligence](https://mlsanity.com/paper/1804.01660/) (2018)
- [Detecting Information Relays in Deep Neural Networks](https://mlsanity.com/paper/2301.00911/) (2023)

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

- [Compression Through Time: An Interplay of Separability, Stationarity and Capacity](https://mlsanity.com/paper/2610.16660/) (2026)

## Abstract (arXiv)

Understanding the internal dynamics of Recurrent Neural Networks (RNNs) is crucial for advancing their interpretability and improving their design. This study introduces an innovative information-theoretic method to identify and analyze information-transfer nodes within RNNs, which we refer to as textitinformation relays. By quantifying the mutual information between input and output vectors across nodes, our approach pinpoints critical pathways through which information flows during network operations. We apply this methodology to both synthetic and real-world time series classification tasks, employing various RNN architectures, including Long Short-Term Memory (LSTM) networks and Gated Recurrent Units (GRUs). Our results reveal distinct patterns of information relay across different architectures, offering insights into how information is processed and maintained over time. Additionally, we conduct node knockout experiments to assess the functional importance of identified nodes, significantly contributing to explainable artificial intelligence by elucidating how specific nodes influence overall network behavior. This study not only enhances our understanding of the complex mechanisms driving RNNs but also provides a valuable tool for designing more robust and interpretable neural networks.