How LLMs Work102 · Module V · Lesson 31 of 31
Quiz · 10 min

Quiz: The mechanism

Twenty questions on the pipeline from tokens to tokens.

Summary

Twenty questions on the pipeline from tokens to tokens.

Quiz
  1. 01What is a token?

    • A. A character
    • B. A word
    • C. A subword unit chosen by a learned tokenizer
    • D. A byte
    Reveal answer

    C. Tokens are subword units — neither characters nor words.

  2. 02Why does attention need positional encoding?

    • A. Attention is expensive
    • B. Attention is order-invariant by default
    • C. Attention is stochastic
    • D. Attention is autoregressive
    Reveal answer

    B. Without positional encoding, attention treats input as a bag of tokens.

  3. 03What does RoPE do?

    • A. Adds a bias to attention
    • B. Rotates Q and K vectors by position
    • C. Randomizes positions
    • D. Normalizes positions
    Reveal answer

    B. RoPE rotates queries and keys by an angle proportional to position.

  4. 04What is stored in the KV cache?

    • A. Queries
    • B. Keys and values of previous tokens
    • C. Attention scores
    • D. Logits
    Reveal answer

    B. The KV cache stores K and V from prior tokens so they need not be recomputed.

  5. 05What does temperature control?

    • A. Model temperature
    • B. Sharpness of the sampling distribution
    • C. Learning rate
    • D. Context length
    Reveal answer

    B. Temperature scales logits before softmax — lower is sharper, higher is flatter.

  6. 06What does top-p sampling do?

    • A. Picks the top-p tokens by index
    • B. Keeps tokens up to cumulative probability p
    • C. Uses temperature p
    • D. Chooses p random tokens
    Reveal answer

    B. Nucleus sampling keeps the smallest set of tokens whose cumulative probability exceeds p.

  7. 07What does the Chinchilla result say?

    • A. Bigger is always better
    • B. Compute-optimal training scales parameters and data roughly equally
    • C. Fine-tuning is unnecessary
    • D. MoE is optimal
    Reveal answer

    B. Chinchilla: for a fixed compute budget, scale parameters and tokens roughly in proportion.

  8. 08What is speculative decoding?

    • A. Sampling with high temperature
    • B. A draft model predicts, a big model verifies
    • C. Predicting future context lengths
    • D. Beam search variant
    Reveal answer

    B. Speculative decoding uses a small draft model with verification by the big model.

  9. 09What does MoE stand for?

    • A. Model of Everything
    • B. Mixture of Experts
    • C. Multi-order Embedding
    • D. Modular Operator Engine
    Reveal answer

    B. MoE = Mixture of Experts — many small FFNs with a router selecting few per token.

  10. 10Which sampler is the modern default for chat?

    • A. Greedy
    • B. Top-k=40
    • C. Nucleus with p≈0.9
    • D. Beam search
    Reveal answer

    C. Nucleus (top-p) sampling with p around 0.9 is the standard chat default.