Alla Chepurova
screemix
AI & ML interests
Machine learning, ML interpretability, bioinformatics, neuroscience
Recent Activity
upvoted a paper about 16 hours ago
Will It Still Be True Tomorrow? Multilingual Evergreen Question
Classification to Improve Trustworthy QA upvoted a paper 13 days ago
Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines? Organizations
