Lee, D. J., & Heimersheim, S. (2024). Investigating Sensitive Directions in GPT-2: An Improved Baseline and Comparative Analysis of SAEs.
Chicago Style (17th ed.) CitationLee, Daniel J., and Stefan Heimersheim. Investigating Sensitive Directions in GPT-2: An Improved Baseline and Comparative Analysis of SAEs. 2024.
MLA (9th ed.) CitationLee, Daniel J., and Stefan Heimersheim. Investigating Sensitive Directions in GPT-2: An Improved Baseline and Comparative Analysis of SAEs. 2024.
Warning: These citations may not always be 100% accurate.