dilyabareeva.github.io
Feature Visualization has long been a staple interpretability tool. Our work shows it’s far from reliable! 🚨
Feature Visualization has long been a staple interpretability tool. Our work shows it’s far from reliable! 🚨
GitHub: github.com/dilyabareeva...
Paper: arxiv.org/abs/2410.07158
GitHub: github.com/dilyabareeva...
Paper: arxiv.org/abs/2410.07158