Neel Nanda, Jacob Dunefsky, Philippe Chlenski
6 of 7 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; 5 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2406.11944.json · badge: /api/ran/2406.11944.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.
| Repository | Role | Ran |
|---|---|---|
| jacobdunefsky/transcoder_circuits | canonical (classifier label) classifier basis: census |
6 ran · 1 no recorded run |
| Function | Status | Where it lives |
|---|---|---|
| geometric_median_array | Ran ran; our contract draft was wrong, not the code |
jacobdunefsky/transcoder_circuits/sae_training/geom_median/src/geom_median/numpy/weiszfeld_array.py pointer only (licence: NONE) · get_code("7743fdc98d0dc90e") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, jacobdunefsky/transcoder_circuits 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. |
| geometric_median_per_component | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
jacobdunefsky/transcoder_circuits/sae_training/geom_median/src/geom_median/numpy/weiszfeld_array.py pointer only (licence: NONE) · get_code("736db4bd4f1d805e") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, jacobdunefsky/transcoder_circuits 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. |
| get_recons_loss | Ran ran; our contract draft was wrong, not the code |
jacobdunefsky/transcoder_circuits/sae_training/train_sae_on_language_model.py pointer only (licence: NONE) · get_code("109b275bea3f94e9") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, jacobdunefsky/transcoder_circuits 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. |
| get_scheduler | Ran ran; our contract draft was wrong, not the code |
jacobdunefsky/transcoder_circuits/sae_training/optim.py pointer only (licence: NONE) · get_code("72e1b397fe5aa9b2") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, jacobdunefsky/transcoder_circuits 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. |
| sample_uniform | Ran ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT) |
jacobdunefsky/transcoder_circuits/transcoder_circuits/feature_dashboards.py pointer only (licence: NONE) · get_code("4daba25365b65503") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, jacobdunefsky/transcoder_circuits 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. |
| weighted_average | Ran ran, honoured the contract we drafted |
jacobdunefsky/transcoder_circuits/sae_training/geom_median/src/geom_median/numpy/weiszfeld_array.py pointer only (licence: NONE) · get_code("0c1b8e7c5079b759") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, jacobdunefsky/transcoder_circuits 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. |
| sample_percentiles | Not yet run unverified (harvested, no recorded run) |
jacobdunefsky/transcoder_circuits/transcoder_circuits/feature_dashboards.py pointer only (licence: NONE) · get_code("0e24bc34a9a2f735") How it ranThe body of this sample is withheld: GitHub detected no licence in this paper's repository, jacobdunefsky/transcoder_circuits 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. |
Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
A key goal in mechanistic interpretability is circuit analysis: finding sparse subgraphs of models corresponding to specific behaviors or capabilities. However, MLP sublayers make fine-grained circuit analysis on transformer-based language models difficult. In particular, interpretable features-such as those found by sparse autoencoders (SAEs)-are typically linear combinations of extremely many neurons, each with its own nonlinearity to account for. Circuit analysis in this setting thus either yields intractably large circuits or fails to disentangle local and global behavior. To address this we explore transcoders, which seek to faithfully approximate a densely activating MLP layer with a wider, sparsely-activating MLP layer. We introduce a novel method for using transcoders to perform weights-based circuit analysis through MLP sublayers. The resulting circuits neatly factorize into input-dependent and input-invariant terms. We then successfully train transcoders on language models with 120M, 410M, and 1.4B parameters, and find them to perform at least on par with SAEs in terms of sparsity, faithfulness, and humaninterpretability. Finally, we apply transcoders to reverse-engineer unknown circuits in the model, and we obtain novel insights regarding the "greater-than circuit" in GPT2-small. Our results suggest that transcoders can prove effective in decomposing model computations involving MLPs into interpretable circuits. Code is available at https://github.com/jacobdunefsky/transcoder_circuits/.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.11944")
get_code_for_paper("2406.11944")
have("2406.11944")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2406.11944.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2406.11944)
Connect an agent — have() is free.