Sutskever Reading List Map D3 Visualizer

Foundational Research Lineage Map
Interactive D3 Dependency Graph
Attention Is All You Need
Vaswani et al. (2017) • Attention Domain
Attention(Q,K,V) = softmax(QK^T / √d_k)V
Replaces recurrent architectures with self-attention mechanisms, enabling parallelization across token sequences.
Architectural Tensor Sandbox
Live Metric Computations
Presets:
Attention FLOPs 32,768
Total Parameters 198,144
Matrix Dimension 8x64
Gradient Stability Stable (1.02)
Input Tokens
8x64
LayerNorm
Pre-LN
QKV Proj
4 Heads
Softmax
GELU
Attention Weight Matrix Heatmap ($S \times S$) Entropy: 2.15 bits
Sequence Length ($S$) 8
Hidden Dim ($D$) 64
Attention Heads ($H$) 4
LayerNorm Type
Enjoy this tool? Build your own with Super