guidelabs/fineweb-atlas
Viewer • Updated • 1.52B • 6.91k • 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.
Nathaniel-GL
updated a
dataset 2 months ago
What do the concept labels represent?
1
#2 opened 2 months ago
by 
csinva
AyaGL
updated a
model 2 months ago
Update tokenizer_config.json
#6 opened 2 months ago
by 
AyaGL
Update tokenization_steerling.py
#5 opened 2 months ago
by AyaGL
Update modeling_steerling.py
#4 opened 2 months ago
by AyaGL
Update configuration_steerling.py
#3 opened 2 months ago
by AyaGL
Update config.json
#2 opened 2 months ago
by AyaGL
Nathaniel-GL
published a
dataset 3 months ago
juliusadebayo
published a
model 3 months ago
juliusadebayo
updated a
model 3 months ago
juliusadebayo
updated a
Space over 1 year ago
andreasmadsen
authored 6
papers about 2 years ago
Interpretability Needs a New Paradigm
Paper • 2405.05386 • Published • 5
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
andreasmadsen
authored a
paper over 2 years ago