Sparse Autoencoders Find Partially Interpretable Features in Italian Small Language Models

Alessandro Bondielli, Lucia C. Passaro, Alessandro Lenci. Sparse Autoencoders Find Partially Interpretable Features in Italian Small Language Models. In Cristina Bosco, Elisabetta Jezek, Marco Polignano, Manuela Sanguinetti, editors, Proceedings of the Eleventh Italian Conference on Computational Linguistics (CLiC-it 2025), Cagliari, Italy, September 24-26, 2025. Volume 4112 of CEUR Workshop Proceedings, CEUR-WS.org, 2025. [doi]

References

No references recorded for this publication.

Cited by

No citations of this publication recorded.