Related papers: Darkness Visible: Reading the Exception Handler of…
Mechanistic interpretability of transformers requires identifying not just which components matter but how they compose into the computational route that produced a prediction. Both attention and MLP follow a shared key-value template…
We present a mechanistic analysis of literary style in GPT-2, identifying individual neurons that discriminate between exemplary prose and rigid AI-generated text. Using Herman Melville's Bartleby, the Scrivener as a corpus, we extract…
Self-attention mechanism is the key of the Transformer but often criticized for its computation demands. Previous token pruning works motivate their methods from the view of computation redundancy but still need to load the full network and…
Standard transformer architectures apply the same number of layers to every token regardless of contextual difficulty. We present Token-Selective Attention (TSA), a learned per-token gate on residual updates between consecutive transformer…
Large Language Models (LLMs) are widely deployed in real-world applications, yet their internal mechanisms remain difficult to interpret and control, limiting our ability to diagnose and correct undesirable behaviors. Mechanistic…
We study whether a Large Language Model can learn the deterministic sequence of trees generated by the iterated prime factorization of the natural numbers. Each integer is mapped into a rooted planar tree and the resulting sequence $…
We demonstrate that a developmentally ordered curriculum markedly improves reasoning transparency and sample-efficiency in small language models (SLMs). Concretely, we train Cognivolve, a 124 M-parameter GPT-2 model, on a four-stage…
Large language models (LLM) such as OpenAI's ChatGPT and GPT-3 offer unique testbeds for exploring the translation challenges of turning literacy into numeracy. Previous publicly-available transformer models from eighteen months prior and…
A widely cited result by Dong et al. (2021) showed that Transformers built from self-attention alone, without skip connections or feed-forward layers, suffer from rapid rank collapse: all token representations converge to a single…
Recent advances in language model interpretability have identified circuits, critical subnetworks that replicate model behaviors, yet how knowledge is structured within these crucial subnetworks remains opaque. To gain an understanding…
Understanding how individuals with Parkinson's disease (PD) describe cognitive experiences in their daily lives can offer valuable insights into disease-related cognitive and emotional changes. However, extracting such information from…
While large language models (LLMs), such as GPT-3, appear to be robust and general, their reasoning ability is not at a level to compete with the best models trained for specific natural language reasoning problems. In this study, we…
Implicit reasoning is the ability of a language model to solve multi-hop reasoning tasks in a single forward pass, without chain of thought. We investigate this capability using GPT2-style language models trained from scratch on controlled…
The goal of this paper is to explore how Transformer language models process semantic knowledge, especially regarding the plausibility of noun-verb relations. First, I demonstrate GPT2 exhibits a higher degree of similarity with humans in…
This paper presents a new family of backpropagation-free neural architectures, Gated Linear Networks (GLNs). What distinguishes GLNs from contemporary neural networks is the distributed and local nature of their credit assignment mechanism;…
The GPT-3.5 models have demonstrated impressive performance in various Natural Language Processing (NLP) tasks, showcasing their strong understanding and reasoning capabilities. However, their robustness and abilities to handle various…
Transformer-based language models excel at both recall (retrieving memorized facts) and reasoning (performing multi-step inference), but whether these abilities rely on distinct internal mechanisms remains unclear. Distinguishing recall…
Recent advances in large language models (LLMs) have enabled general-purpose systems to perform increasingly complex domain-specific reasoning without extensive fine-tuning. In the medical domain, decision-making often requires integrating…
Transformer-based language models (LMs) are at the core of modern NLP, but their internal prediction construction process is opaque and largely not understood. In this work, we make a substantial step towards unveiling this underlying…
The success of large-scale language models like GPT can be attributed to their ability to efficiently predict the next token in a sequence. However, these models rely on constant computational effort regardless of the complexity of the…