Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,31 @@ sdk: static
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
pinned: false
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# PhillipsLab — University of Utah
|
| 11 |
+
|
| 12 |
+
<img src="https://users.cs.utah.edu/~jeffp/images/utah_logo.png" alt="University of Utah Logo" width="160">
|
| 13 |
+
|
| 14 |
+
## About Us
|
| 15 |
+
**PhillipsLab** is part of the Kahlert School of Computing at the University of Utah, led by Prof. Jeff M. Phillips.
|
| 16 |
+
|
| 17 |
+
We study **interpretable AI**, **activation steering** and **dataset curation**.
|
| 18 |
+
Our work bridges theory and application — from understanding internal representations in large language models to make models more truthful and safe .
|
| 19 |
+
|
| 20 |
+
## Research Focus
|
| 21 |
+
- Representation and activation steering in large language models
|
| 22 |
+
- Dataset design for interpretable and steerable AI
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
## Purpose of this Hub
|
| 26 |
+
This Hugging Face organization hosts:
|
| 27 |
+
- Private and public **datasets** for steering and interpretability research
|
| 28 |
+
- Experiment **models** and **evaluation code**
|
| 29 |
+
- Collaborative resources for our research group
|
| 30 |
+
|
| 31 |
+
## Contact
|
| 32 |
+
**Prof. Jeff M. Phillips**
|
| 33 |
+
🌐 [users.cs.utah.edu/~jeffp](https://users.cs.utah.edu/~jeffp/)
|
| 34 |
+
|
| 35 |
+
---
|
| 36 |
+
|
| 37 |
+
*PhillipsLab © 2025 — University of Utah*
|