PhillipsLab/formal_informal_contrast
Viewer • Updated • 1k • 18
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
PhillipsLab — University of Utah
Kahlert School of Computing · Led by Prof. Jeff M. Phillips
Interpretable AI · Activation Steering · Dataset Curation
📊 Featured Datasets
- Conciseness ↔ Verbosity Contrast — minimal pairs isolating conciseness vs verbosity for interpretability and activation steering.
- Positivity ↔ Negativity Contrast — stance-style pairs controlling positive vs negative sentiment while keeping factual parity.
PhillipsLab © 2025 — University of Utah
models 0
None public yet
datasets 6
PhillipsLab/positivity_negativity_contrast
Viewer • Updated • 1.06k • 9
PhillipsLab/conciseness_verbosity_contrast
Viewer • Updated • 994 • 5
PhillipsLab/axbench-steering-data
Viewer • Updated • 5.75k • 6
PhillipsLab/weekdays_activations
Viewer • Updated • 49 • 5
PhillipsLab/weekdays_prompts
Viewer • Updated • 49 • 21