Pith. sign in

REVIEW 5 cited by

How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.00586 v5 pith:SRPBUEJT submitted 2023-04-30 cs.CL cs.AIcs.LG

Michael Hanna , Ollie Liu , Alexandre Variengien This is my paper
classification cs.CLcs.AIcs.LG
keywords gpt-2smallabilitiescircuitlanguagemathematicalpre-trainedyear
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Pre-trained language models can be surprisingly adept at tasks they were not explicitly trained on, but how they implement these capabilities is poorly understood. In this paper, we investigate the basic mathematical abilities often acquired by pre-trained language models. Concretely, we use mechanistic interpretability techniques to explain the (limited) mathematical abilities of GPT-2 small. As a case study, we examine its ability to take in sentences such as "The war lasted from the year 1732 to the year 17", and predict valid two-digit end years (years > 32). We first identify a circuit, a small subset of GPT-2 small's computational graph that computes this task's output. Then, we explain the role of each circuit component, showing that GPT-2 small's final multi-layer perceptrons boost the probability of end years greater than the start year. Finally, we find related tasks that activate our circuit. Our results suggest that GPT-2 small computes greater-than using a complex but general mechanism that activates across diverse contexts.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 14 citations worldwide. Full citation record

  1. Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race

    cs.CL 2025-05 conditional novelty 7.0 of 10

    Alignment on Llama 3 reduces explicit bias but amplifies implicit bias, because aligned models no longer represent 'black' and 'white' as racial concepts in ambiguous contexts.

  2. Pretraining Curricula Enable Selective Fine-tuning

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Imbalanced pretraining curricula disentangle task circuits in transformers, improving in-context learning and the selectivity of refusal fine-tuning relative to balanced training.

  3. Geometry of Reason: Spectral Signatures of Valid Mathematical Reasoning

    cs.LG 2026-01 reject novelty 6.0 of 10

    Spectral features of attention are claimed to classify proof validity with near-perfect effect sizes, but the main evaluation relabels proofs using the classifier's own outputs.

  4. From Indirect Object Identification to Syllogisms: Exploring Binary Mechanisms in Transformer Circuits

    cs.CL 2025-08 conditional novelty 5.0 of 10

    GPT-2 small performs syllogisms through truth-copying attention heads and a suppression-plus-MLP pathway that can output a negated truth value.

  5. NEAT: Concept driven Neuron Attribution in LLMs

    cs.CL 2025-08 reject novelty 4.0 of 10

    NEAT identifies concept neurons by feeding a single mean hidden-state vector through the model and ranking neurons by their effect on concept-word probabilities.

Pith tools