Layer-wise Target Propagation: Efficient Component Attribution through Target Centric Propagation

arXiv:2603.19742 · cs.LG, cs.CL · Submitted 2026-03-20 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-03-20

Updated: 2026-09-24

Code: https://github.com/lab-paper-code/dual_

Terminology

• Dual Path Attribution — 63× in this paper
• Transformer — 45× in this paper · explained in 2 episodes
• Benchmark — 19× in this paper · explained in 2 episodes
• Activation Patching — 13× in this paper · explained in 2 episodes
• Interpretability — 10× in this paper · explained in 15 episodes
• AUC — 7× in this paper · explained in 2 episodes
• Embeddings — 6× in this paper · explained in 2 episodes
• Gated Linear Unit — 6× in this paper
• Indirect Object Identification — 6× in this paper
• Multi-Head Self-Attention — 4× in this paper
• Transformer Architecture — 4× in this paper · explained in 2 episodes
• Decoupling — 3× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Layer-wise Relevance Propagation — 3× in this paper
• Ablation — 2× in this paper · explained in 1 episode
• Attention Mechanism — 2× in this paper · explained in 2 episodes
• Empirical Methods in Natural Language Processing — 2× in this paper
• Information Flow Routes — 2× in this paper
• Trace — 2× in this paper · explained in 2 episodes
• AI Alignment — 1× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Activation Function — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Allocator — 1× in this paper · explained in 1 episode
• Direct Logit Attribution — 1× in this paper
• Fidelity — 1× in this paper · explained in 2 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Layer-wise Relevance Propagation (LRP) — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes

Sources

• The Shattered Gradients Problem: If resnets are the answer, then what is the question?
• Eliciting Latent Predictions from Transformers with the Tuned Lens
• Towards Automated Circuit Discovery for Mechanistic Interpretability
• Extraction of Salient Sentences from Labelled Documents
• XAI for Transformers: Better Explanations through Conservative Propagation
• A Primer on the Inner Workings of Transformer-based Language Models
• Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space
• The Llama 3 Herd of Models
• Mistral 7B
• DePass: Unified Feature Attributing by Simple Decomposed Forward Pass
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• SmoothGrad: removing noise by adding noise
• Know What You Don't Know: Unanswerable Questions for SQuAD
• GLU Variants Improve Transformer
• RoFormer: Enhanced Transformer with Rotary Position Embedding
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Learning Important Features Through Propagating Activation Differences
• Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small
• Qwen3 Technical Report
• Qwen2.5 Technical Report

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks