Unsupervised latent identity search surfaces entities like catalpa tree and Chinese spirit
Sauers_ · x · 2026-10-19
The author shares an unsupervised "latent identity search" experiment: without predefined labels, the method automatically surfaces entities such as the catalpa tree and "Chinese spirit" from a model's latent space. This is an interpretability-oriented exploration showing how unsupervised methods can uncover specific identities and concepts encoded inside models.
More from Research
- FloatDoor: backdoors that trigger LLM misbehavior only on specific GPUs and platforms — rickasaurus · 2026-10-19
- G. Rauch on new interpretability piece: simpler path may beat SOTA mech interp — yenkel · 2026-10-19
- Burkov's Hundred-Page Language Models Book details three architectures with PyTorch code — burkov · 2026-10-19
- FOMO-DEX from Amazon FAR, CMU and Berkeley uses force feedback to fix only contact commands — HaozhiQ · 2026-10-19
- Preprint finds virus-specific T cells persistently activated in 40% of Long COVID cases — alvelda · 2026-10-19
- New evidence suggests consciousness is a dynamic flow, not a static thing — AnnaCiaunica · 2026-10-19