Skip to content
conftrace_

latent space direction

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

multi-attribute editing (1) refusal suppression (1) semantic manipulation (1) self-organizing map (1) interpretable representation (1) model ablation (1) mechanistic interpretability (1) generative adversarial network (1) latent space (1) safety alignment (1)

Papers

SOM Directions Are Better than One: Multi-Directional Refusal Suppression in Language Models AAAI 2026 Discovering Interpretable Latent Space Directions of GANs Beyond Binary Attributes CVPR 2021