引導式測驗 · 中等 等級
變壓器感應頭測驗
查看歸納前綴匹配、前置驅動資訊、跨層電路、訓練觀察和上下文學習機制的限制。
問題 1 的 8
感應頭本質上執行什麼規則?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- 感應頭本質上執行什麼規則?
- 預測語言中最常見的標記
- 始終複製前一個令牌不變
- 隨機打亂上下文標記
- 之前查看[A][B],然後再次在[A]上預測[B]
- What capability was linked to induction-head behavior in the cited 2022 study?
- In-context learning in the examined models, with broader large-model claims framed as hypotheses
- A proof that every form of reasoning uses only one identical circuit
- Changing the tokenizer vocabulary during every prompt
- Permanent weight updates whenever a repeated token appears
- 「前令牌頭」在感應電路中扮演什麼角色?
- 它產生最終的softmax
- 它刪除了位置訊息
- 它向前複製每個令牌的前任訊息,以便可以進行匹配
- 它規範了注意力權重
- 規範感應電路通常涉及多少個注意力頭?
- 正好一個
- 二、跨層組合
- 單層數百個
- 零;它只是前饋
- What training relationship did the induction-head study report in the models it examined?
- Head formation coincided with changes in loss behavior and increased in-context learning
- All heads were fully formed before any training
- Induction behavior could only appear after every parameter was frozen forever
- The same exact training transition must occur in every future model
- 感應頭最直接處理哪一項任務?
- 計算數值梯度
- 壓縮模型的權重
- 加密輸入提示
- 透過複製先前匹配標記後面的內容來重複序列
- What roles do query-key matching and the output-value path play in the canonical induction circuit?
- Query-key computations generate the final text filename; output-value computations train the tokenizer
- Query-key computations select the matching context position; output-value computations promote the token information there
- Both paths only count the total number of context words
- The output-value path selects a position without any attention pattern
- Does a demonstrated two-head induction circuit prove that every large-model in-context task uses that mechanism alone?
- Yes; every architecture and prompt has already been causally tested
- Yes; no other network computation can influence a prediction
- No; the wider explanation remains a hypothesis needing model- and task-specific evidence
- Only the number of parameters determines whether the proof is universal