Sparse autoencoders trained on Titanet speaker embeddings yield latent units that identify and steer language and music features, replicating LLM-style feature splitting and steering in audio data.
Towards monosemanticity: Decomposing language models with dictionary learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
Sparse Autoencoder Insights on Voice Embeddings
Sparse autoencoders trained on Titanet speaker embeddings yield latent units that identify and steer language and music features, replicating LLM-style feature splitting and steering in audio data.