Ekdeep Singh @ ICML
@ekdeepl.bsky.social
Postdoc at CBS, Harvard University
(New around here)
(New around here)
Paper alert––*Awarded best paper* at NeurIPS workshop on Foundation Model Interventions! 🧵👇
We analyze the (in)abilities of SAEs by relating them to the field of disentangled rep. learning, where limitations of AE based interpretability protocols have been well established!🤯
We analyze the (in)abilities of SAEs by relating them to the field of disentangled rep. learning, where limitations of AE based interpretability protocols have been well established!🤯
December 18, 2024 at 1:45 PM
Paper alert––*Awarded best paper* at NeurIPS workshop on Foundation Model Interventions! 🧵👇
We analyze the (in)abilities of SAEs by relating them to the field of disentangled rep. learning, where limitations of AE based interpretability protocols have been well established!🤯
We analyze the (in)abilities of SAEs by relating them to the field of disentangled rep. learning, where limitations of AE based interpretability protocols have been well established!🤯