Representation Engineering: Mistral-7B on Acid (via) Theia Vogel provides a delightfully clear explanation (and worked examples) of control vectors—a relatively recent technique for influencing the behaviour of an LLM by applying vectors to the hidden states that are evaluated during model inference.
These vectors are surprisingly easy to both create and apply. Build a small set of contrasting prompt pairs—“Act extremely happy” v.s. “Act extremely sad” for example (with a tiny bit of additional boilerplate), then run a bunch of those prompts and collect the hidden layer states. Then use “single-component PCA” on those states to get a control vector representing the difference.
The examples Theia provides, using control vectors to make Mistral 7B more or less honest, trippy, lazy, creative and more, are very convincing.
Recent articles
- OpenAI DevDay: Let’s build developer tools, not digital God - 2nd October 2024
- OpenAI DevDay 2024 live blog - 1st October 2024
- Weeknotes: Three podcasts, two trips and a new plugin system - 30th September 2024