| kind: nla_dataset | |
| schema_version: 2 | |
| dataset_id: av_sft_train.parquet | |
| split_type: av_sft | |
| row_count: 124741 | |
| extraction: | |
| d_model: 4096 | |
| injection_scale: null | |
| mse_scale: sqrt_d_model | |
| norm: none | |
| tokens: | |
| injection_char: ㈎ | |
| injection_token_id: 149705 | |
| injection_left_neighbor_id: 29 | |
| injection_right_neighbor_id: 522 | |
| 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.' | |