Alessandro Bondielli
alessandrobondielli
AI & ML interests
NLP, multimodal, Mechanistic Interpretability
Recent Activity
published a dataset about 1 month ago
alessandrobondielli/LAION-2B-ita-preview updated a dataset about 1 month ago
alessandrobondielli/LAION-2B-ita-preview updated a dataset 6 months ago
colinglab/EXPLAINITA-task2Organizations
-
Open Problems in Mechanistic Interpretability
Paper • 2501.16496 • Published • 22 -
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Paper • 2503.18878 • Published • 121 -
Geospatial Mechanistic Interpretability of Large Language Models
Paper • 2505.03368 • Published • 13
-
Open Problems in Mechanistic Interpretability
Paper • 2501.16496 • Published • 22 -
I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders
Paper • 2503.18878 • Published • 121 -
Geospatial Mechanistic Interpretability of Large Language Models
Paper • 2505.03368 • Published • 13