Papers › Attention Approximates Sparse Distributed Memory

Attention Approximates Sparse Distributed Memory

10 Nov 2021NeurIPS 2021 12arXiv:2111.05498archive 2025-07-28

Trenton Bricken, Cengiz Pehlevan

While Attention has come to be an important mechanism in deep learning, there remains limited intuition for why it works so well. Here, we show that Transformer Attention can be closely related under certain data conditions to Kanerva's Sparse Distributed Memory (SDM), a biologically plausible associative memory model. We confirm that these conditions are satisfied in pre-trained GPT2 Transformer models. We discuss the implications of the Attention-SDM map and provide new computational and biological interpretations of Attention.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 19 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 12 ran (7 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 12 samples that ran has no recorded date.

trentbrick/attention-approximates-sdm officialmentioned in paperjaxMITSyntology: 19 samples, 12 ran (5 instrument-failed) · 7 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

19 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
5ran · our draft was wrong
5ran
7unverified

Licence: 7 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. For 7 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from trentbrick/attention-approximates-sdm. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

trentbrick/attention-approximates-sdm official repository 19 samples, 12 ran (5 instrument-failed) · 7 unverified
check_number_comma in 14 papers HugFace/src/transformers/convert_slow_tokenizer.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · a727df5fd2f5599a · report fixture: signature piece:str/0/str · returned bool · level recorded 2026-09-24
cosine_to_hamm SDM_Circ_Inter_Funcs.py ran fingerprinted MIT (permissive) · 0a85051c7ca5e520 · report fixture: signature cosines:Tensor/1/float, n:int/0/int · returned Tensor · level recorded 2026-09-24
ensure_valid_input in 15 papers HugFace/src/transformers/convert_graph_to_onnx.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · d770e1dd1d799a47 · report fixture: signature model:callable/0/?, tokens:dict/0/?, input_names:list/1/str · returned tuple · level recorded 2026-09-24
f in 68 papers
census: 17 implementations from 15 papers, 17 distinct outputs across 7 buckets, one shared input per bucket
HugFace/SDM_Circ_Inter_Funcs.py ran MIT (permissive) · 7cedca63fc0c0ef4 · report fixture: signature x:ndarray/0/float, c_p:ndarray/0/float · returned float64 · level recorded 2026-09-24
gelu_fast in 39 papers HugFace/src/transformers/activations.py ran · our draft was wrong fingerprinted MIT (permissive) · a4475703ff58ecf9 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
gelu_new in 55 papers
census: 3 implementations from 7 papers, 1 distinct output on one shared input
HugFace/src/transformers/activations.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 45bb87451230d5e8 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
generate_identified_filename in 15 papers HugFace/src/transformers/convert_graph_to_onnx.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 7efe3db5c9e2f94d · report fixture: signature filename:PosixPath/0/?, identifier:str/0/str · returned PosixPath · level recorded 2026-09-24
hamm_to_cosine SDM_Circ_Inter_Funcs.py ran fingerprinted MIT (permissive) · 02bdc6d03c9e9398 · report fixture: signature hamms:ndarray/1/int, n:int/0/int · returned ndarray · level recorded 2026-09-24
mish in 95 papers
census: 5 implementations from 8 papers, 1 distinct output on one shared input
HugFace/src/transformers/activations_tf.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · cc8c8c3ebf0c343f · report fixture: signature x:ndarray/2/float · returned EagerTensor · level recorded 2026-09-26
optimal_p_and_ham HugFace/SDM_Circ_Inter_Funcs.py ran fingerprinted MIT (permissive) · c0614eb63596689f · report fixture: signature m:int/0/int, r:int/0/int, n:int/0/int · returned tuple · level recorded 2026-09-24
quick_gelu in 43 papers HugFace/src/transformers/activations.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · e21f72f1a9834aef · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
softmax in 240 papers
census: 53 implementations from 63 papers, 16 distinct outputs across 8 buckets, one shared input per bucket
SDM_Circ_Inter_Funcs.py ran fingerprinted MIT (permissive) · df0360e77dc451b9 · report fixture: signature x:ndarray/1/float, beta:float/0/float · returned ndarray · level recorded 2026-09-24
convert_slow_tokenizer in 14 papers HugFace/src/transformers/convert_slow_tokenizer.py unverified MIT (permissive) · 9339ca51cea1f469 · report
fit_beta Implementations_Associative_Memory.py unverified MIT (permissive) · 4ffbc66e592539d9 · report
infer_shapes in 15 papers HugFace/src/transformers/convert_graph_to_onnx.py unverified MIT (permissive) here; the stored copy is pointer only · 3449d7d975edfb89 · report
test_projection utils_LearnProjections.py unverified MIT (permissive) · 53ca5e262920709d · report
train_projection utils_LearnProjections.py unverified MIT (permissive) · ad63033a1bd00f97 · report
update_Binary_Neuron_SDM Implementations_Associative_Memory.py unverified MIT (permissive) · 26f72e9fdbfa1b09 · report
update_Cont_Attention Implementations_Associative_Memory.py unverified MIT (permissive) · 7380c3067187ef0e · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections