# Emergence of Quantised Representations Isolated to Anisotropic Functions

arXiv: https://arxiv.org/abs/2507.12070 · HTML: https://mlsanity.com/paper/2507.12070/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 16 Jul 2025.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Prevalence of Neural Collapse during the terminal phase of deep learning training](https://mlsanity.com/paper/2008.08186/) (2020)
- [Network Dissection: Quantifying Interpretability of Deep Visual Representations](https://mlsanity.com/paper/1704.05796/) (2017)
- [Dynamic Routing Between Capsules](https://mlsanity.com/paper/1710.09829/) (2017)
- [On the Symmetries of Deep Learning Models and their Internal Representations](https://mlsanity.com/paper/2205.14258/) (2022)
- [The Spotlight Resonance Method: Resolving the Alignment of Embedded Activations](https://mlsanity.com/paper/2505.13471/) (2025)

## Built on by (most cited first, 2 of 2)

- [The Affine Divergence: Aligning Activation Updates Beyond Normalisation](https://mlsanity.com/paper/2512.22247/) (2025)
- [Isotropic Activation Functions Enable Deindividuated Neurons and Adaptive Topologies](https://mlsanity.com/paper/2602.23405/) (2026)

## Abstract (arXiv)

Presented is a novel methodology for determining representational structure, which builds upon the existing Spotlight Resonance method. This new tool is used to gain insight into how discrete representations can emerge and organise in autoencoder models, through a controlled ablation study that alters only the activation function. Using this technique, the validity of whether function-driven symmetries can act as implicit inductive biases on representations is determined. Representations are found to tend to discretise when the activation functions are defined through a discrete algebraic permutation-equivariant symmetry. In contrast, they remain continuous under a continuous algebraic orthogonal-equivariant definition. This confirms the hypothesis that the symmetries of network primitives can carry unintended inductive biases, leading to task-independent artefactual structures in representations. The discrete symmetry of contemporary forms is shown to be a strong predictor for the production of symmetry-organised discrete representations emerging from otherwise continuous distributions -- a quantisation effect. This motivates further reassessment of functional forms in common usage due to such unintended consequences. Moreover, this supports a general causal model for a mode in which discrete representations may form, and could constitute a prerequisite for downstream interpretability phenomena, including grandmother neurons, discrete coding schemes, general linear features and a type of Superposition. Hence, this tool and proposed mechanism for the influence of functional form on representations may provide insights into interpretability research. Finally, preliminary results indicate that quantisation of representations correlates with a measurable increase in reconstruction error, reinforcing previous conjectures that this collapse can be detrimental.