# Sparse Autoencoder Insights on Voice Embeddings

arXiv: https://arxiv.org/abs/2502.00127 · HTML: https://mlsanity.com/paper/2502.00127/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in SAE features and their applications, one of 13 directions in Mechanistic interpretability.
- Builds on 11 of its 14 references that are in the map.
- First posted on arXiv 31 Jan 2025.

## Placed in

- Mechanistic interpretability / [SAE features and their applications](https://mlsanity.com/mechinterp/sae-features-and-their-applications/)

## Builds on (most cited first, 11 of 11)

- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Scaling and evaluating sparse autoencoders](https://mlsanity.com/paper/2406.04093/) (2024)
- [Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2](https://mlsanity.com/paper/2408.05147/) (2024)
- [TitaNet: Neural Model for speaker representation with 1D Depth-wise separable convolutions and global context](https://mlsanity.com/paper/2110.04410/) (2021)
- [DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systems](https://mlsanity.com/paper/1906.10263/) (2019)
- [Explainable Attribute-Based Speaker Verification](https://mlsanity.com/paper/2405.19796/) (2024)
- [Leveraging speaker attribute information using multi task learning for speaker verification and diarization](https://mlsanity.com/paper/2010.14269/) (2020)

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

- [On the Interpretability of Whisper Encodings Using Sparse Autoencoders](https://mlsanity.com/paper/2605.12225/) (2026)

## Abstract (arXiv)

Recent advances in explainable machine learning have highlighted the potential of sparse autoencoders in uncovering mono-semantic features in densely encoded embeddings. While most research has focused on Large Language Model (LLM) embeddings, the applicability of this technique to other domains remains largely unexplored. This study applies sparse autoencoders to speaker embeddings generated from a Titanet model, demonstrating the effectiveness of this technique in extracting mono-semantic features from non-textual embedded data. The results show that the extracted features exhibit characteristics similar to those found in LLM embeddings, including feature splitting and steering. The analysis reveals that the autoencoder can identify and manipulate features such as language and music, which are not evident in the original embedding. The findings suggest that sparse autoencoders can be a valuable tool for understanding and interpreting embedded data in many domains, including audio-based speaker recognition.