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
This event is also part of the public calendar streams below, so visitors can return to the broader series instead of only this single page.
Time
10 Nov 2026 17:30 to 10 Nov 2026 19:00
Venue
ETH HG Hauptgebäude, Zurich
ETH HG Hauptgebäude, Zurich, ch
Publisher
Zurich AI Safety
Public calendars carrying this event
Duration
1 hour 30 min
Responsible
Zurich AI Safety
Source details
- Original event
- https://luma.com/zais-42em
- Import status
- Regional Scan
- Source kind
- Native
- Updated
- 1 day ago
- Public calendars
- Switzerland Tech Events
Event map
ETH HG Hauptgebäude, Zurich, ch
Map data © OpenStreetMap contributors
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