SONAR SAEs
Collection
Sparse Auto-Encoders for SONAR sentence embeddings, from Pochinkov & Darmawan (2025) (EACL submission). • 5 items • Updated
SONAR SAEs — additional runs
Additional SAE training runs on SONAR embeddings that are not directly cited in:
Interpretability of Text Auto-Encoders using Sparse Auto-Encoders: A Sandbox for Interpreting Neuralese. Nicky Pochinkov & Jason Rich Darmawan, EACL 2026 (submitted).
Provided for completeness and reproducibility (early
hyper-parameter sweeps, exploratory runs that didn't make the paper).
Match wandb run IDs against
nickypro/sonar-saes-wandb-logs for training metrics.
The canonical SAEs are in
nickypro/sonar-saes-large (scaled-up BatchTopK) and
nickypro/sonar-saes-comparison (four-variant comparison).
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support