PaperScope
LIVE · 2026-09-29 05:40 UTC

Identifying Temporal Features within Transcoders for Time Sensitive Factual Recall

Sanjay Govindan, Yang Song, Maurice Pagnucco

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.33183 v1
Category
Submitted
2026-09-27

Abstract

Large Language Models (LLMs) suffer from temporal misalignment, often due to the contradictory nature of their training corpora. While current mitigation strategies rely on computationally expensive fine-tuning or context-heavy retrieval augmented generation (RAG), the internal mechanisms governing time-sensitive recall remain under-explored. Unlike prior studies that identify temporal components such as attention heads and MLP layers, we provide the first feature-level map of temporal recall by isolating individual MLP features via transcoder circuit tracing. We identify three node categories (common temporal, common to the year, and chrono-semantic) which interact to generate a temporal filter during factual recall. By analysing Gemma 2 2B, LLaMA 3.2 1B, and Qwen3-4B, we show that these features do not follow a simple linear pipeline but represent time through a parallel and mixed syntactic-semantic interplay across layers. We additionally discover a class of higher-layer temporal components invisible to existing EAP-IG methods, establishing transcoders as a more complete lens for temporal interpretability in time-sensitive factual recall. These findings present MLP components for potential targeted interventions in time-sensitive factual recall

Comment: EMNLP Findings 2026

arXiv abs page · PDF · same-day batch