← Back to all news
arXiv Machine Learning By Daniil Ognev, C\'elian Vasson, Lijie Hu, Kentaro Inui, Benjamin Heinzerling

SharedSAE: One Feature Dictionary Across Language Models

Read the original on arXiv Machine Learning →

SharedSAE demonstrates that a single sparse autoencoder can replace multiple model‑specific SAEs by using a shared dictionary with model‑specific encoder‑decoder pairs. It preserves activation magnitudes, normalizes only selection scores, and supports single‑model inference via model dropout. Trained on four 1B‑scale language models, SharedSAE retains 96.6% of the mean explained variance of dedicated SAEs, shows higher cross‑model latent correlations, and allows efficient adaptation of new models to the shared latent space.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

Hugging Face Trending Papers
Aug 13

SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization

Sparse autoencoders (SAEs) are proposed to extract numerous features from large language model (LLM) representations, yet explaining these features still relies primarily on external observation. This reliance leads to superficial explanations inferred from observed model behavior and computational inefficiency from collecting such behavioral evidence at scale.

llms
More like this →
arXiv Machine Learning
Oct 16

Diminishing Returns of Data in Sparse Autoencoders: Functional Behavior does not Guarantee Feature Reproducibility

Sparse autoencoders (SAEs) are usually trained on hundreds of millions to billions of activation tokens, but this study shows that the amount of data needed depends on the evaluation metric. Training four SAE architectures on three language models with token budgets from 5 M to 500 M revealed that reconstruction quality can reach near‑full‑data performance with far fewer tokens, while one‑to‑one feature reproducibility continues to improve as more data is used. The research also found that random sampling preserves activation distributions better for reconstruction, whereas diversity‑based sampling can enhance feature interpretability, and provided a theoretical framework distinguishing statistical consistency from the stricter conditions needed for exact feature recovery.

By Sambit Ghosh, Madelyn Mathai, R. Venkatesh Babu, Chirag Agarwal
llms
More like this →