Causal Proxy Models

university

https://github.com/frankaging/Causal-Proxy-Model

Activity Feed Request to join this org

AI & ML interests

Causal Proxy Models For Concept-Based Model Explanations

Recent Activity

zhengxuanzenwu authored a paper 9 months ago

Rigorously Assessing Natural Language Explanations of Neurons

zhengxuanzenwu authored a paper 9 months ago

MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions

zhengxuanzenwu authored a paper 9 months ago

A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments

View all activity

models 28

CPMs/cpm.in.lstm.inclusive.seed66

Updated Oct 14, 2022 • 12

CPMs/cpm.in.lstm.approximate.seed66

Updated Oct 14, 2022 • 13

CPMs/cpm.in.lstm.approximate.seed77

Updated Oct 14, 2022 • 9

CPMs/cpm.in.lstm.inclusive.seed42

Updated Oct 14, 2022 • 11

CPMs/cpm.in.lstm.inclusive.seed77

Updated Oct 14, 2022 • 11

CPMs/cpm.in.lstm.approximate.seed42

Updated Oct 14, 2022 • 11

CPMs/cpm.in.gpt2.approximate.seed42

Updated Oct 14, 2022 • 11

CPMs/cpm.in.gpt2.inclusive.seed77

Updated Oct 14, 2022 • 9

CPMs/cpm.in.gpt2.inclusive.seed42

Updated Oct 14, 2022 • 10

CPMs/cpm.in.gpt2.approximate.seed77

Updated Oct 14, 2022 • 12

datasets

None public yet