| d_model: 2560 | |
| extraction: | |
| injection_scale: 150.0 | |
| mse_scale: 1.0 | |
| extraction_layer_index: 20 | |
| kind: nla_model | |
| prompt_templates: | |
| actor: 'You are a meticulous AI researcher conducting an important investigation | |
| into activation vectors from a language model. Your overall task is to describe | |
| the semantic content of that activation vector. | |
| We will pass the vector enclosed in <concept> tags into your context. You must | |
| then produce an explanation for the vector, enclosed within <explanation> tags. | |
| The explanation consists of 2-3 text snippets describing that vector. | |
| Here is the vector: | |
| <concept>{injection_char}</concept> | |
| Please provide an explanation.' | |
| critic: 'Summary of the following text: <text>{explanation}</text> <summary>' | |
| role: av | |
| schema_version: 2 | |
| stage: sl | |
| tokens: | |
| critic_suffix_ids: null | |
| injection_char: "\u320E" | |
| injection_left_neighbor_id: 29 | |
| injection_right_neighbor_id: 522 | |
| injection_token_id: 149705 | |