guidelabs/fineweb-atlas
Viewer • Updated • 1.52B • 537 • 9
AI & ML interests
We build interpretable models and AI systems that can reliably explain their reasoning, and are easy to audit, steer, and understand.
Recent Activity
View all activity
Nathaniel-GL
updated a
dataset 25 days ago
What do the concept labels represent?
1
#2 opened 28 days ago
by 
csinva
AyaGL
updated a
model 30 days ago
Update tokenizer_config.json
#6 opened about 1 month ago
by 
AyaGL
Update tokenization_steerling.py
#5 opened about 1 month ago
by AyaGL
Update modeling_steerling.py
#4 opened about 1 month ago
by AyaGL
Update configuration_steerling.py
#3 opened about 1 month ago
by AyaGL
Update config.json
#2 opened about 1 month ago
by AyaGL
Nathaniel-GL
published a
dataset about 1 month ago
juliusadebayo
published a
model about 2 months ago
juliusadebayo
updated a
model about 2 months ago
juliusadebayo
updated a
Space over 1 year ago
andreasmadsen
authored a
paper almost 2 years ago
andreasmadsen
authored 6
papers about 2 years ago
Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
Paper • 2110.08412 • Published • 1
Faithfulness Measurable Masked Language Models
Paper • 2310.07819 • Published
Measuring Arithmetic Extrapolation Performance
Paper • 1910.01888 • Published
Neural Arithmetic Units
Paper • 2001.05016 • Published
Post-hoc Interpretability for Neural NLP: A Survey
Paper • 2108.04840 • Published
Can Large Language Models Explain Themselves?
Paper • 2401.07927 • Published • 4