Prerequisites for Truth Directions and Linear Probes

Direct prerequisites (2)

1. Mechanistic Interpretability: Features, Circuits, and Causal Faithfulnesslayer 4, tier 1
2. Residual Stream and Transformer Internalslayer 4, tier 2

Reachable through the chain (32)

These topics are not directly cited as prerequisites but are reached transitively by following the chain upward. Working through the direct prerequisites pulls these in.

• Transformer Architecturelayer 4, tier 2
• Attention Mechanism Theorylayer 4, tier 2
• Matrix Operations and Propertieslayer 0A, tier 1
• Sets, Functions, and Relationslayer 0A, tier 1
• Basic Logic and Proof Techniqueslayer 0A, tier 2
• Softmax and Numerical Stabilitylayer 1, tier 1
• Feedforward Networks and Backpropagationlayer 2, tier 1
• Differentiation in Rnlayer 0A, tier 1
• Vectors, Matrices, and Linear Mapslayer 0A, tier 1
• Continuity in Rⁿlayer 0A, tier 1
• Metric Spaces, Convergence, and Completenesslayer 0A, tier 1
• Matrix Calculuslayer 1, tier 1
• The Jacobian Matrixlayer 0A, tier 1
• The Hessian Matrixlayer 0A, tier 1
• Eigenvalues and Eigenvectorslayer 0A, tier 1
• Activation Functionslayer 1, tier 1
• Convex Optimization Basicslayer 1, tier 1
• Principal Component Analysislayer 1, tier 1
• Singular Value Decompositionlayer 0A, tier 1
• Sparse Autoencoders for Interpretability: TopK, JumpReLU, Matryoshka, and Scalinglayer 4, tier 1
• Autoencoderslayer 2, tier 2
• Lasso Regressionlayer 2, tier 1
• Linear Regressionlayer 1, tier 1
• Maximum Likelihood Estimation: Theory, Information Identity, and Asymptotic Efficiencylayer 0B, tier 1
• Common Probability Distributionslayer 0A, tier 1
• Central Limit Theoremlayer 0B, tier 1
• Law of Large Numberslayer 0B, tier 1
• Random Variableslayer 0A, tier 1
• Kolmogorov Probability Axiomslayer 0A, tier 1
• Expectation, Variance, Covariance, and Momentslayer 0A, tier 1
• KL Divergencelayer 1, tier 1
• Information Theory Foundationslayer 0B, tier 2