๐
๐
Old Age
Prune, Interpret, Evaluate: A Cross-Layer Transcoder-Native Framework for Efficient Circuit Discovery via Feature Attribution
April 18, 2026 ยท Grace Period ยท + Add venue
Authors
Qinhao Chen, Linyang He, Nima Mesgarani
arXiv ID
2604.16889
Category
cs.CL: Computation & Language
Citations
0
Abstract
Existing feature-interpretation pipelines typically operate on uniformly sampled units, but only a small fraction of cross-layer transcoder (CLT) features matter for a target behavior, with the rest resulting in expensive feature explaining and evaluating costs. We introduce the first CLT-native end-to-end framework, PIE, connecting Pruning, automatic Interpretation, and interpretation Evaluation, enabling systematic measurement of behavioral fidelity and downstream interpretability under pruning. To achieve this, we propose Feature Attribution Patching (FAP), a patch-grounded attribution method that scores CLT features by aggregating gradient-weighted write contributions, and FAP-Synergy, a synergy-aware reranking procedure. We evaluate pruning using KL-divergence behavior retention and assess interpretation quality with FADE-style metrics. Across IOI and Doc-String, across budgets $K \in \{50, 100, 200, 400, 800\}$, and across FAP, FAP-Synergy, Activation-Magnitude, and ACDC-style pruning, the FAP family consistently achieves the best or near-best fidelity, with FAP-Synergy providing its clearest gains in strict-budget regimes. On IOI with CLTs for Llama-3.2-1B and Gemma-2-2B, pruning to $K=100$ features matches the KL fidelity that random selection from the active feature set requires $\approx 4$k features to achieve ($\approx 40\times$ compression), enabling $\approx 40\times$ fewer interpretation/evaluation calls while substantially reducing low-quality features.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Computation & Language
๐
๐
Old Age
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
๐
๐
Old Age
XLNet: Generalized Autoregressive Pretraining for Language Understanding
๐ฎ
๐ฎ
The Ethereal
Effective Approaches to Attention-based Neural Machine Translation
๐
๐
Old Age
A large annotated corpus for learning natural language inference
๐
๐
Old Age