SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2301.05217 · 2023

Progress measures for grokking via mechanistic interpretability

Jacob Steinhardt, Lawrence Chan, Neel Nanda, Tom Lieberum, Jess Smith

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2301.05217.json · badge: /api/ran/2301.05217.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
mechanistic-interpretability-grokking/progress-measures-paper canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
FunctionStatusWhere it lives
make_fourier_basis Ran
ran, honoured the contract we drafted
mechanistic-interpretability-grokking/progress-measures-paper/transformers.py
pointer only (licence: NONE) · get_code("ac16158072424173")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mechanistic-interpretability-grokking/progress-measures-paper when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

calculate_key_freqs Not yet run
unverified (harvested, no recorded run)
mechanistic-interpretability-grokking/progress-measures-paper/transformers.py
pointer only (licence: NONE) · get_code("898cc031d0d5683c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mechanistic-interpretability-grokking/progress-measures-paper when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

get_components_of_trig_loss Not yet run
unverified (harvested, no recorded run)
mechanistic-interpretability-grokking/progress-measures-paper/transformers.py
pointer only (licence: NONE) · get_code("d54cf7af8b321052")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mechanistic-interpretability-grokking/progress-measures-paper when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Neural networks often exhibit emergent behavior, where qualitatively new capabilities arise from scaling up the amount of parameters, training data, or training steps. One approach to understanding emergence is to find continuous progress measures that underlie the seemingly discontinuous qualitative changes. We argue that progress measures can be found via mechanistic interpretability: reverseengineering learned behaviors into their individual components. As a case study, we investigate the recently-discovered phenomenon of "grokking" exhibited by small transformers trained on modular addition tasks. We fully reverse engineer the algorithm learned by these networks, which uses discrete Fourier transforms and trigonometric identities to convert addition to rotation about a circle. We confirm the algorithm by analyzing the activations and weights and by performing ablations in Fourier space. Based on this understanding, we define progress measures that allow us to study the dynamics of training and split training into three continuous phases: memorization, circuit formation, and cleanup. Our results show that grokking, rather than being a sudden shift, arises from the gradual amplification of structured mechanisms encoded in the weights, followed by the later removal of memorizing components.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2301.05217")
get_code_for_paper("2301.05217")
have("2301.05217")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2301.05217.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2301.05217.svg)](https://syntology.ai/paper/2301.05217)

Connect an agent — have() is free.