pyvene

pyvene's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

zhengxuanzenwu 

updated 4 models 28 days ago

pyvene/gemma-reft-r1-9b-it-res

Updated 28 days ago

pyvene/gemma-reft-r1-2b-it-res

Updated 28 days ago

pyvene/gemma-diffmean-2b-it-res

Updated 28 days ago

pyvene/gemma-diffmean-9b-it-res

Updated 28 days ago

zhengxuanzenwu 

updated a dataset 30 days ago

pyvene/axbench-concept16k_v2

Viewer • Updated 30 days ago • 3.46M • 178

zhengxuanzenwu 

updated a collection 30 days ago

AxBench Release

Collection

Open supervised dictionary learning models and datasets for Gemma 2 2B and 9B instruction-tuned models. • 13 items • Updated 30 days ago • 5

zhengxuanzenwu 

published a dataset 30 days ago

pyvene/axbench-concept16k_v2

Viewer • Updated 30 days ago • 3.46M • 178

zhengxuanzenwu 

in pyvene/gemma-reft-r1-2b-it-res about 1 month ago

README updates

#1 opened about 1 month ago by

neuronpedia

zhengxuanzenwu 

updated a collection about 1 month ago

AxBench Release

Collection

Open supervised dictionary learning models and datasets for Gemma 2 2B and 9B instruction-tuned models. • 13 items • Updated 30 days ago • 5

zhengxuanzenwu 

updated a dataset about 1 month ago

pyvene/axbench-conceptFD

Viewer • Updated Jan 30 • 5.33k • 147 • 2

zhengxuanzenwu 

published a dataset about 1 month ago

pyvene/axbench-conceptFD

Viewer • Updated Jan 30 • 5.33k • 147 • 2

zhengxuanzenwu 

updated a Space about 1 month ago

Running on Zero

2

2

SDL-ReFT-cr1

🫠

Guide chatbot with specific topics

zhengxuanzenwu 

updated a collection about 1 month ago

AxBench Release

Collection

Open supervised dictionary learning models and datasets for Gemma 2 2B and 9B instruction-tuned models. • 13 items • Updated 30 days ago • 5

zhengxuanzenwu 

updated a Space about 1 month ago

Running on Zero

2

2

SDL-ReFT-r1

🤔

Guide conversations with specific topics

zhengxuanzenwu 

authored 5 papers 11 months ago

Rigorously Assessing Natural Language Explanations of Neurons

Paper • 2309.10312 • Published Sep 19, 2023

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

Paper • 2305.14795 • Published May 24, 2023

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

Paper • 2401.12631 • Published Jan 23, 2024

ReFT: Representation Finetuning for Language Models

Paper • 2404.03592 • Published Apr 4, 2024 • 94

pyvene: A Library for Understanding and Improving PyTorch Models via Interventions

Paper • 2403.07809 • Published Mar 12, 2024 • 1