SourceWhen Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
The paper trains a prefix of size 10 on GPT-2 for the emotion classification task and examines the range of attention (1st to 99th percentile) over the 10 prefix positions across 12 layers. For most layers, including layer 1, the attention each prefix position receives is almost constant regardless of the input, meaning the effective bias is a single fixed vector applied to the attention layer output. Only layer 3 shows three prefix positions with large variation, yielding a 3-dimensional effective subspace where the input governs which bias vector is selected. This suggests GPT-2 does not fully utilize the representational capacity available to the prefix.