Distinct Steering Vectors With Low Cosine Similarity Can Steer the Same Concept
benno_krojer · x · 2026-10-28
Researcher Benno Krojer adds an observation to his paper thread: some of their steering vectors have low cosine similarity with each other — two quite distinct vectors that still steer the same concept well. This hints there may be many sets of steering directions that work similarly well, though they might manifest somewhat differently. The work includes a paper, demo, and open-source code; first author Donghao did research for the first time.
More from Research
- Samaya's 30B post-trained model beats frontier on financial research at 11x lower cost — maithra_raghu · 2026-10-29
- Scaling cross-situational word learning: 2,441 hours of child-perspective video from Stanford team — RichmanRonald · 2026-10-29
- Curiosity algorithms need world models plus locomotor primitives to replicate animal behavior — aran_nayebi · 2026-10-29
- Virtual fly study finds autonomous exploration maximizes population-level state coverage — aran_nayebi · 2026-10-29
- Indie researcher publishes SGTE, a from-scratch alternative inference architecture to beat the scaling wall — ReportProfessional57 · 2026-10-29
- Neuron persona library grows to 180k+ personas: single neurons make LLMs claim to be Jesus — CatAstro_Piyush · 2026-10-29