Rzadkie autoenkodery do quizu dotyczącego wyodrębniania cech

Odpowiedzi i wyjaśnienia pojawiają się w miarę rozwiązywania quizu.

1. Which interpretability difficulty motivates sparse dictionary learning for neural activations?
   • Every model activation is already a complete dictionary definition
   • Several learned signals can overlap in an activation space
   • The tokenizer must be permanently removed
   • All neural weights are stored as image pixels
2. What does an SAE sparsity constraint encourage for a given input?
   • Every feature to activate equally on every input
   • A mandatory removal of its decoder
   • A guarantee that every feature has exactly one perfect human label
   • Only a limited subset of learned feature activations to be nonzero
3. Jaka była słynna przykładowa funkcja w pracy Anthropic „Scaling Monosemanticity”?
   • Funkcja mostu Golden Gate
   • Funkcja dla liczby siedem
   • Funkcja dostępna wyłącznie dla koloru niebieskiego
   • Funkcja dla samogłosek
4. What does an overcomplete SAE dictionary mean?
   • It must activate every feature for every token
   • It contains no reconstruction mapping
   • It has more learned feature directions than input activation dimensions
   • It always requires less storage than the input vector
5. What does a monosemantic feature label aim to describe in this research context?
   • A guarantee that the feature never responds to related examples
   • A feature associated with one interpretable concept
   • A language model that has only one parameter
   • A token represented by exactly one raw byte
6. W jaki sposób można wykorzystać SAE, aby wpłynąć na zachowanie modelu?
   • Poprzez włączenie lub wyłączenie funkcji w celu sterowania wyjściami
   • Poprzez przeszkolenie całego modelu od zera
   • Usuwając tokenizer
   • Konwertując go na model obrazu
7. What does an SAE’s reconstruction residual measure for an activation vector?
   • The difference between two unrelated document titles
   • The total number of words in the model vocabulary
   • Only the model’s hardware temperature
   • The difference between the original activation and its decoded reconstruction
8. When an SAE is fitted to collected activations of a frozen language model, which weights need to be trained for that fitting?
   • Every original language-model weight must be updated
   • Only the tokenizer’s character list
   • The SAE’s own encoder and decoder weights
   • No parameters of the SAE can change