Vision Bias Steering
LLM steering experiments for shifting model outputs between spatial and descriptive language.

Brief
Study whether inference-time steering can shift captions between spatial and descriptive language without retraining model weights.
Approach
Train and validate steering vectors, run local and multi-model sweeps, then compare language behavior through evaluation and plotting utilities.
Technical focus
PyTorch experimentation, NNSight interventions, reproducible sweeps, and language-model evaluation.
View project results
- 616K+
- COCO captions filtered
- 28.9%
- RMS next-token bias reduction
- <0.1%
- output degeneration