← Back to all news
arXiv Machine Learning By Sambit Ghosh, Madelyn Mathai, R. Venkatesh Babu, Chirag Agarwal

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

Read the original on arXiv Machine Learning →

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.

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

arXiv Machine Learning
Jun 18

From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability

arXiv:2606. 18383v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable features from language models (LMs), yet a central question remains: when can an SAE-based explanation be treated as a faithful view of an underlying frozen LM We study this through a post-hoc generalization framework that certifies the LM via a sparse proxy, obtained by replacing a native hidden activation with its pretrained SAE reconstruction.

By Dibyanayan Bandyopadhyay, Asif Ekbal
llmsefficiencysafety
More like this →
arXiv Machine Learning
Sep 7

SharedSAE: One Feature Dictionary Across Language Models

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.

By Daniil Ognev, C\'elian Vasson, Lijie Hu, Kentaro Inui, Benjamin Heinzerling
llms
More like this →