AI Safety Weekly: Steering Vectors & Input Optimisation
Steering vectors are a relatively simple way of influencing model behaviour. A direction is given to the model’s internal activations for a given concept, and the behaviour shifts accordingly. But such vectors require full access to the model’s internals. Is there a way to automa
Este evento también forma parte de los flujos públicos de calendario de abajo, para que los visitantes vuelvan a la serie completa y no solo a esta página.
Horario
10 Nov 2026 17:30 a 10 Nov 2026 19:00
Lugar
ETH HG Hauptgebäude, Zurich
ETH HG Hauptgebäude, Zurich, ch
Publicador
Zurich AI Safety
Calendarios públicos que incluyen este evento
Duration
1 hora 30 min
Responsible
Zurich AI Safety
Source details
- Original event
- https://luma.com/zais-42em
- Import status
- Regional Scan
- Source kind
- Nativo
- Updated
- hace 1 día
- Public calendars
- Switzerland Tech Events
Mapa del evento
ETH HG Hauptgebäude, Zurich, ch
Datos del mapa © colaboradores de OpenStreetMap
Steering vectors are a relatively simple way of influencing model behaviour. A direction is given to the model’s internal activations for a given concept, and the behaviour shifts accordingly. But such vectors require full access to the model’s internals. Is there a way to automatically optimise an input to induce the same behaviour as a steering vector? Can this input be transferred to different Price / conditions: free