AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Quiet Feature Learning in Algorithmic Tasks

Prudhviraj Naidu, Zixian Wang, Leon Bergen, Ramamohan Paturi

AAAI 2026 · Architectures and efficiency › RNNs and normalization · approach: Layer-wise analysis of language models · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
keep carry feature (vs ablating it) (ablation)Transformer++ on Addition · Addition (16)test accuracy (%): 58.8 -> 100Improved
keep carry feature (vs ablating it) (ablation)Transformer++ on Addition · Addition (64)test accuracy (%): 24.9 -> 100Improved
keep first_operand feature (vs ablating it) (ablation)Transformer++ on Addition · Addition (32)test accuracy (%): 7.00 -> 100Improved
keep first_operand feature (vs ablating it) (ablation)Transformer++ on Addition · Addition (16)test accuracy (%): 100 -> 100No clear effect
keep first_operand feature (vs ablating it) (ablation)Transformer++ on Multiplication · Multiplication (16)test accuracy (%): 76.8 -> 76.8No clear effect
keep carry feature (vs ablating it) (ablation)Transformer++ on Multiplication · Multiplication (16)test accuracy (%): 76.8 -> 56.4Improved
keep queue feature (vs ablating it) (ablation)Transformer++ on BFS · Breadth first search (11)test accuracy (%): 99.7 -> 54.6Improved
keep is_prev_negative feature (vs ablating it) (ablation)Transformer++ on Maximum Subarray · Maximum Subarray (64)test accuracy (%): 95.6 -> 89.9Improved
ablate random direction instead of quiet feature (ablation)Transformer++ · Addition (16) carrytest accuracy (%): 100 -> 100No clear effect
increase compute budget past slow phaseTransformer++ on algorithmic tasks · six of ten taskscompute-optimal validation lossMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy