Do the activation signatures of neural networks on fixed probes contain behavioral information?
🤝 Open to Collab
Maximus Powers
maximuspowers
AI & ML interests
Data science, information theory, physics
Recent Activity
published a model about 15 hours ago
maximuspowers/stenographer updated a model 1 day ago
maximuspowers/stenographerOrganizations
A study benchmarking major LLM's internalized philosophies, results can be found here: https://philosophai-results.vercel.app/ (view 07-2025 data)
-
maximuspowers/bert-philosophy-classifier
Text Classification • 0.1B • Updated • 25 -
maximuspowers/philosophai-mcq-benchmark
Viewer • Updated • 100 • 5 -
maximuspowers/philosophy-schools-multilabel
Viewer • Updated • 5.67k • 43 -
maximuspowers/philpapers-papers-summarized-labeled
Viewer • Updated • 3.78k • 43 • 2
Social bias detection resources used to create a multi-label token classification model for: Generalizations, Unfairness, and Stereotypes
-
Gusnet V1 Demo
⚡2Identify biased entities in text
-
GUS-Net: Social Bias Classification in Text with Generalizations, Unfairness, and Stereotypes
Paper • 2410.08388 • Published • 2 -
ethical-spectacle/social-bias-ner
Token Classification • Updated • 281 • 4 -
ethical-spectacle/gus-dataset-v1
Viewer • Updated • 3.74k • 37
Do the activation signatures of neural networks on fixed probes contain behavioral information?
Social bias detection resources used to create a multi-label token classification model for: Generalizations, Unfairness, and Stereotypes
-
Gusnet V1 Demo
⚡2Identify biased entities in text
-
GUS-Net: Social Bias Classification in Text with Generalizations, Unfairness, and Stereotypes
Paper • 2410.08388 • Published • 2 -
ethical-spectacle/social-bias-ner
Token Classification • Updated • 281 • 4 -
ethical-spectacle/gus-dataset-v1
Viewer • Updated • 3.74k • 37
A study benchmarking major LLM's internalized philosophies, results can be found here: https://philosophai-results.vercel.app/ (view 07-2025 data)
-
maximuspowers/bert-philosophy-classifier
Text Classification • 0.1B • Updated • 25 -
maximuspowers/philosophai-mcq-benchmark
Viewer • Updated • 100 • 5 -
maximuspowers/philosophy-schools-multilabel
Viewer • Updated • 5.67k • 43 -
maximuspowers/philpapers-papers-summarized-labeled
Viewer • Updated • 3.78k • 43 • 2