The paper investigates natural language autoencoders (NLAs) as tools for verbalizing activation differences in large language models. It examines whether NLAs capture compositional structure, generalize to fine‑tuned models, recover fine‑tuning objectives, and can be specialized for model diffing. Experiments across four models show that NLAs largely succeed in these tasks, though they do not yet match state‑of‑the‑art diffing methods on emergent misalignment detection.
By Andrea Blasi N\'u\~nez, Gianluca Barmina, Federico Torrielli, Thiusius Rajeeth Savarimuthu, Peter Schneider-Kamp, Lukas Galke Poech
The paper investigates natural language autoencoders (NLAs) that convert large language model activations into readable text. It examines whether NLAs capture compositional structure, generalize to fine‑tuned models, recover fine‑tuning objectives, and can be specialized for model diffing. Experiments across multiple models show positive results: NLAs preserve compositionality, transfer to lightweight fine‑tunes, recover hidden objectives, and outperform a black‑box baseline on diffing tasks, though they lag behind state‑of‑the‑art methods for misalignment detection.
arXiv:2610.18727v2 Announce Type: replace
Abstract: Natural Language Autoencoders (NLAs) are proposed as oversight tools for language models: an Activation Verbaliser (AV) writes an English explanati...
By Kevin Yandoka Denamgana\"i
The paper investigates whether the tokens highlighted by large language models (LLMs) as key to their predictions are behaviorally consistent when those tokens are manipulated. Using sufficiency, comprehensiveness, and counterfactuality metrics, the authors evaluate closed‑source GPT‑4o‑mini and open‑source models Gemma3, Granite8B, and DeepSeek on IMDB and Steam review datasets. Results show that GPT‑4o‑mini consistently follows expected patterns, Gemma3 and Granite8B maintain sufficiency but falter under stricter interventions, and DeepSeek variants exhibit structural inconsistencies, indicating that explanation reliability varies across model families and sizes.
By Alisson Rosa Pereira, Bruno Iochins Grisci
arXiv:2607. 20379v1 Announce Type: new Abstract: Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed faithful if the activation can be regenerated from it.
By Hiskias Dingeto
arXiv:2408.11827v2 Announce Type: replace
Abstract: Understanding how language models compose meaning from linguistic input remains a central problem in interpretability research. Mechanistic studies...
By Nura Aljaafari, Danilo S. Carvalho, Andr\'e Freitas
arXiv:2610.20139v1 Announce Type: new
Abstract: Sparse autoencoders (SAEs) have emerged as a promising approach to mechanistic interpretability by decomposing language-model activations into sparse,...
By Salima Lamsiyah, Adelaide Danilov, Oleksandr Marchenko Breneur, Aria Nourbakhsh
The paper introduces a new task called reconciliatory explanation generation, where large language models (LLMs) must produce explanations that make contradictory statements compatible. It proposes reusing natural language inference datasets and new quality metrics for scalable evaluation. Experiments with 13 LLMs show limited success, especially when longer reasoning chains are involved, but reinforcement‑learning training improves performance on two narrative reasoning benchmarks.
By Jason Chan, Zhixue Zhao, Robert Gaizauskas
arXiv:2603. 01437v2 Announce Type: replace Abstract: As chain of thought (CoT) has become central to scaling reasoning capabilities in large language models (LLMs), it has also emerged as a promising tool for interpretability, suggesting the opportunity to understand model decisions through verbalized reasoning.
By Kyle Cox, Darius Kianersi, Adri\`a Garriga-Alonso
arXiv:2603. 28371v2 Announce Type: replace-cross Abstract: When an agent can articulate why something works, we typically take this as evidence of genuine understanding.
By Camilo Chac\'on Sartori
arXiv:2607. 15495v1 Announce Type: cross Abstract: Out of everything the human brain processes, only a small fraction is consciously accessible, in the sense of being available for verbal report, deliberate control, and flexible reasoning.
By Wes Gurnee, Nicholas Sofroniew, Adam Pearce, Mateusz Piotrowski, Isaac Kauvar, Runjin Chen, Anna Soligo, Paul Bogdan, Euan Ong, Rowan Wang, Ben Thompson, David Abrahams, Subhash Kantamneni, Emmanuel Ameisen, Joshua Batson, Jack Lindsey
The paper introduces a method for analyzing how interventions in a prompt affect a language model’s reasoning by using behavioral counterfactuals. It trains a module to edit the residual stream so that the next-token distributions for a fixed response match between a source and a counterfactual prompt, outperforming standard activation reconstruction. The resulting attribution maps and visualizations help identify causally important locations for counterfactual recovery and guide hypothesis testing with activation patching, as demonstrated in a case study on Gemma-4-E4B-it and DeepSeek-R1-0528-Qwen3-8B.
By Shawn Im, James Oldfield, Adel Bibi, Sharon Li