引導式測驗 · 中等 等級
Logit 透鏡與中間層解碼測驗
測試中間殘差讀數、歸一化和非嵌入、調諧仿射探針、詞彙 Logits、softmax 和因果解釋的限制。
問題 1 的 8
What readout does a plain logit lens reuse to obtain vocabulary scores from an intermediate state?
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。
- What readout does a plain logit lens reuse to obtain vocabulary scores from an intermediate state?
- A required new image classifier for every layer
- The model's appropriate final normalization and unembedding output projection
- A random dictionary sort with no model parameters
- A separate retrained tokenizer for each prompt
- Why can the same output projection be applied mathematically at multiple residual-stream depths?
- Every layer must contain an identical copy of the final state
- The entire transformer is a single linear mapping
- All intermediate token scores are guaranteed identical
- The states have compatible hidden dimensions, although their representations may not be equally calibrated for that readout
- 相對於普通 Logit 鏡頭,「調諧鏡頭」解決了什麼問題?
- 它透過學習的仿射變換來糾正每層的不匹配
- 它消除了任何非嵌入的需要
- 它使模型的推理速度更快
- 它用 argmax 取代了 softmax
- If an intermediate lens readout favors a correct factual token, what has been directly observed?
- The unique causal location of the model's factual knowledge
- A guarantee that all later output will be correct
- That the particular probe maps that state to a high score for the token
- The exact reasoning process of a conscious system
- Logit 透鏡最直接的用途是什麼?
- 壓縮模型權重
- 語言之間的翻譯
- 加密模型已激活
- 觀察深度預測如何以及在何處形成
- Why can a plain final-head readout be misleading on early transformer states?
- Early states always use a different vocabulary file
- Their representation distributions can differ from the final state for which the head was trained
- Every early-layer vector is necessarily unstructured noise
- No matrix operation can be applied before the final layer
- A lens uses a model with a fifty-thousand-entry vocabulary and a 768-dimensional hidden state. How many vocabulary logits does its unembedding produce?
- 768, one score per hidden coordinate only
- One, because the token must be chosen before projection
- Fifty thousand, one score per vocabulary entry
- Exactly the number of transformer layers
- What does softmax add to a logit-lens vocabulary-score display?
- A normalized distribution over the projected vocabulary scores
- Proof that every displayed probability is a calibrated belief
- A causal intervention on the model's hidden states
- A replacement for the output projection's vocabulary dimension