Rigorously Assessing Natural Language Explanations of Neurons
Paper
•
2309.10312
•
Published
Causal Proxy Models
university
AI & ML interests
Causal Proxy Models For Concept-Based Model Explanations
CPMs's activity
zhengxuanzenwu
authored
5
papers
11 months ago
MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions
Paper
•
2305.14795
•
Published
A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments
Paper
•
2401.12631
•
Published
ReFT: Representation Finetuning for Language Models
Paper
•
2404.03592
•
Published
•
94
pyvene: A Library for Understanding and Improving PyTorch Models via Interventions
Paper
•
2403.07809
•
Published
•
1
zhengxuanzenwu
authored
2
papers
12 months ago
KarelDO
authored
a
paper
over 1 year ago
zhengxuanzenwu
authored
a
paper
over 1 year ago
zhengxuanzenwu
authored
a
paper
almost 2 years ago
KarelDO
updated
10
models
over 2 years ago
CPMs/cpm.in.lstm.inclusive.seed66
Updated
•
13
CPMs/cpm.in.lstm.approximate.seed66
Updated
•
9
CPMs/cpm.in.lstm.approximate.seed77
Updated
•
10
CPMs/cpm.in.lstm.inclusive.seed42
Updated
•
11
CPMs/cpm.in.lstm.inclusive.seed77
Updated
•
10
CPMs/cpm.in.lstm.approximate.seed42
Updated
•
8
CPMs/cpm.in.gpt2.approximate.seed42
Updated
•
14
CPMs/cpm.in.gpt2.inclusive.seed77
Updated
•
9
CPMs/cpm.in.gpt2.inclusive.seed42
Updated
•
8
CPMs/cpm.in.gpt2.approximate.seed77
Updated
•
9