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
Cet événement fait aussi partie des flux publics de calendrier ci-dessous, afin que les visiteurs reviennent à la série complète.
Horaire
10 Nov 2026 17:30 à 10 Nov 2026 19:00
Lieu
ETH HG Hauptgebäude, Zurich
ETH HG Hauptgebäude, Zurich, ch
Diffuseur
Zurich AI Safety
Calendriers publics contenant cet événement
Duration
1 heure 30 min
Responsible
Zurich AI Safety
Source details
- Original event
- https://luma.com/zais-42em
- Import status
- Regional Scan
- Source kind
- Natif
- Updated
- il y a 1 jour
- Public calendars
- Switzerland Tech Events
Carte de l’événement
ETH HG Hauptgebäude, Zurich, ch
Données cartographiques © contributeurs 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