transformers

Nearly every candidate can recite softmax(QKᵀ/√d_k)V. What the interviewer is after is the variance derivation and the precise training failure the scale heads off. This is the response that tells rote recall apart from real grasp.

A tidy fundamentals question that trips up anyone who only knows GPT. The signal is pairing each architecture to its task through its attention pattern, and explaining why the field settled on decoder-only even for tasks that are not generation. Here is that answer.

Cross-attention is how a model attends from one sequence into another, the mechanism behind encoder-decoder models and multimodal conditioning. What shows depth is knowing exactly where the queries versus keys/values come from.

Attention gets all the attention, but the feed-forward layers hold most of a transformer's weights and handle much of the per-token 'knowledge' work. What shows depth is knowing what the FFN computes and why it dominates the parameter count.

Both are conditional compute, but one scales parameters and the other scales depth. The signal is knowing which axis each routes along and why that shifts the FLOP story. Here is the sharp version.

One triangle of negative infinity, added before the softmax, is what makes transformer training parallel and generation stubbornly serial. Interviewers want the mechanism and the asymmetry it creates, not a definition of attention read back to them.

Two defaults that every Llama-class model shares and almost no candidate can justify. One is a compute win that turned out to cost nothing in quality; the other is what makes a 60-layer stack converge at all.

Most candidates answer with the 2015 ResNet answer and stop. The senior answer treats the residual stream as a shared communication bus, and that reframing is what makes logit attribution, the logit lens, and activation steering possible at all.

The from-scratch implementation that frontier labs and NVIDIA really do ask. Writing it shows you grasp shapes, the scale factor, the causal mask, and how heads split and recombine. Here is a correct, readable implementation plus the follow-ups.

Single-head attention shows up often; multi-head layers on the split-into-heads, attend-per-head, concatenate pattern. What gets scored is the reshape into heads plus a sharp explanation of why several heads help. Here is the implementation.

RoPE is why modern LLMs extrapolate to longer contexts, and it works by rotation, not addition. Coding it shows you truly understand how position enters attention. Here is the implementation.

Plain multi-head attention is rarely the whole exercise: the usual extension is to chain it into KV-cached decoding and GQA in one sitting. The locked answer walks the NumPy implementation, the equivalence check that proves your cache is correct, and the reshape bugs that silently corrupt attention.