Pith. sign in

Paper Citation Record · LEDGER

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning

As of 10 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 1 inbound Pith citation observation for arXiv:2505.24360.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.24360 v3

Coverage vector

measured 55 of 55 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:30:08.427831Z

measured 56 of 56 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-29T07:03:08.655446Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-06-29T07:03:12.641768Z

Reference resolution

55 of 55 outbound references displayed

  • verified exact0
  • verified fuzzy35
  • unresolved20
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3ef46fd8-58ee-4217-a33f-2e628c6ae624 · outbound

This paper cites Language mod- els can explain neurons in language models.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Language mod- els can explain neurons in language models

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:16.470353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:03.259224Z digest=sha256:0038aceb7c41f054cb7c9002acee1425d97545418b9cb0ee62f274b8c17aee7b

Observation 2f89b2f9-2b59-4f51-8ec5-2ec6bb53f877 · outbound

This paper cites an unresolved cited work.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Unresolved cited work

Reference 2

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:30:16.331927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:03.375453Z digest=sha256:2a649ae42a251c59d160518b301ee04d19a0ee2505146dccb83502b7c96b1b64

Observation e91fabe4-8514-45b4-a502-d8e93d302800 · outbound

This paper cites Towards monosemanticity: Decomposing language mod- els with dictionary learning.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Towards monosemanticity: Decomposing language mod- els with dictionary learning

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T12:30:03.452298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:30:03.452298Z digest=sha256:bba9b9b7d126e2d08487376500f9b449a5599e2a8f5b764497dc88761b4f9fdc

Observation 0b729deb-a105-456f-98bd-79f889060742 · outbound

This paper cites Thread: Circuits.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Thread: Circuits

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:16.104404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:03.599213Z digest=sha256:670a660554bb0562f2e97b133b472c5f4f0beda3d6789bafe53def7d6552a4c1

Observation 81ce14af-b5f6-4040-8712-1e8825c82ec6 · outbound

This paper cites Extracting Training Data from Diffusion Models.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Extracting Training Data from Diffusion Models

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-07T12:30:03.692540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:30:03.692540Z digest=sha256:318f044ba2638d282e81270ac9f525ea3d4c1b3579fedab981eb7d9d54d5f116

Observation 3670e0a5-3aa0-45c9-ab82-0a45606d9644 · outbound

This paper cites Activation atlas.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Activation atlas

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:15.974892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:03.772737Z digest=sha256:e4904e0eb8a0665e2320f353e907013aac58cd158d8dd01668f1ebd04a55dfe1

Observation b2788b2d-648a-43fe-ad66-258085818b62 · outbound

This paper cites Improving Steering Vectors by Targeting Sparse Autoencoder Features.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Improving Steering Vectors by Targeting Sparse Autoencoder Features

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-07T12:30:03.859840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:30:03.859840Z digest=sha256:9c537b0da5118b803a5bb79548b5ee56fc9cc484d4a6bfb98d67dd1a0b18e658

Observation 50284402-015e-4d65-bd1a-b46dc8e3aa94 · outbound

This paper cites Be- yond surface statistics: Scene representations in a latent dif- fusion model, 2023.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Be- yond surface statistics: Scene representations in a latent dif- fusion model, 2023

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:15.824770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:03.942310Z digest=sha256:17d2083f3c8e5da8a3d2f2f515f4a385488e2bac7a87553f81a0a7f2ca104c54

Observation 54d15f3c-f705-4faf-a04b-bf0e19a4d299 · outbound

This paper cites A Synthetic Modal Generation of Additive Manufacturing Roughness Surfaces from Images.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning A Synthetic Modal Generation of Additive Manufacturing Roughness Surfaces from Images

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-07T12:30:04.103640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:30:04.103640Z digest=sha256:5ea73be7d625bab6c90d9e0786f35111f5da70040b09ab92dcba17d4e1dfe19d

Observation 93b9d63c-11fc-4d27-a31d-906e650187bd · outbound

This paper cites Saeuron: Interpretable concept unlearning in diffusion models with sparse autoen- coders, 2025.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Saeuron: Interpretable concept unlearning in diffusion models with sparse autoen- coders, 2025

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:15.674940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:04.210741Z digest=sha256:7d2149118f42398f5b9dca655e5a7a85993cfa8b9a84d617e4df180298379c03

Observation 192ae960-f802-4692-89ae-0d74d81fb6e9 · outbound

This paper cites Interpreting and steering features in images.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Interpreting and steering features in images

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:15.456623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:04.274892Z digest=sha256:3db54980631d9530b3a2eb3e30b2d1a902d45a3fe9e54ea95cd82866638e073e

Observation a092ef3f-b18b-49f4-9641-f9413dc0b11d · outbound

This paper cites Qlora: Efficient finetuning of quantized llms,.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Qlora: Efficient finetuning of quantized llms,

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T12:30:04.386428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:30:04.386428Z digest=sha256:e1c822a27bfa7ee19aabd6c5d39e17c51ad087ef531eb11eccb0c9e14e3cb237

Observation 81b658c3-ebd8-463c-abd3-c611e4204d55 · outbound

This paper cites Toy models of superposition.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Toy models of superposition

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:15.193944Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:04.480213Z digest=sha256:e2d087800e5ddb48cd5bae254322d9e3e88bc6a41e2a349733307d6bb6c4efc6

Observation 30661ab2-8b57-48cd-9581-15a19beedac7 · outbound

This paper cites Scaling rectified flow trans- formers for high-resolution image synthesis, 2024.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Scaling rectified flow trans- formers for high-resolution image synthesis, 2024

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:14.913220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:04.578160Z digest=sha256:6af3b9e7966486ce4367c35591ddc85648496f9b6f7f1a152e5613a30574fcff

Observation 0fb5db83-e18c-4ca8-9818-d9c5e57edfdb · outbound

This paper cites Towards multimodal interpretability: Learning sparse interpretable features in vision transformers.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Towards multimodal interpretability: Learning sparse interpretable features in vision transformers

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:14.649650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:04.675014Z digest=sha256:562540ff26cece922e02b5981bce30475ee6936dc892e83c2f4197fb67ff57af

Observation 50047331-b296-4c3e-8094-434033d35a2e · outbound

This paper cites Concept sliders: Lora adaptors for precise control in diffusion models, 2023.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Concept sliders: Lora adaptors for precise control in diffusion models, 2023

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:14.384356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:04.762833Z digest=sha256:983f526070065fbba7f25fa97aea0768092d44d96051e2218973c37808a8c894

Observation 210c5085-d87b-46cc-a40a-373cc3c0b647 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Scaling and evaluating sparse autoencoders

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-07T12:30:04.848601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:30:04.848601Z digest=sha256:a89212d4781db9db16e498603e70b5113d3cd5f619e101a59db8df47b366dacb

Observation abfad2f5-dc3c-4522-92aa-92e2075e0e07 · outbound

This paper cites Sparse autoencoders can interpret randomly ini- tialized transformers, 2025.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Sparse autoencoders can interpret randomly ini- tialized transformers, 2025

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:14.226829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:04.956836Z digest=sha256:680fbb79ecff5a7b9157bb3c32698a9444a2fa1067db7afcbfa71e240c2f1837

Observation 38dcfa19-8126-458b-bbe7-7c350119315c · outbound

This paper cites Denoising Diffusion Probabilistic Models.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Denoising Diffusion Probabilistic Models

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T12:30:05.041456Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:30:05.041456Z digest=sha256:f4c2f87fd52c646552716202d13245e4a257b6317f3aa75cd7b95f0c8b494373

Observation 24043157-ae80-45a7-a98b-b29755a02df7 · outbound

This paper cites Arbitrary style transfer in real-time with adaptive instance normalization, 2017.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Arbitrary style transfer in real-time with adaptive instance normalization, 2017

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:14.032693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:05.125911Z digest=sha256:8c8b6e75b02a0fdd500b02c55e465203bb0c969ef02fb976aaf42df7ff572ac1

Observation 9c88babc-8bc7-49ac-91f0-6475f6dd94a3 · outbound

This paper cites Sparse autoencoders find highly interpretable features in language models.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Sparse autoencoders find highly interpretable features in language models

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:13.841335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:05.192808Z digest=sha256:1aabd95f1b2230ee2957949ae684228df6a8965d44010b4966b4b336d1080884

Observation 335bcf63-dbbf-4966-9033-b82eff1b4d29 · outbound

This paper cites an unresolved cited work.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Unresolved cited work

Reference 22

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:30:13.572974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:05.262690Z digest=sha256:c979feeab9f3a597db6f2874b2c79bb3d4894e57af4b2b3085d71d553d8ade45

Observation e57c74e9-fa58-467e-bc03-626224369142 · outbound

This paper cites Understanding and steering Llama 3, 2024.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Understanding and steering Llama 3, 2024

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:13.402268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:05.336892Z digest=sha256:4d8c7eeeb54732826c83ba60c2e70b7d0a6d7cfea01c3f6badb69a2d86d00c43

Observation 4e7a6e3b-dff6-4e7b-9c9a-fcd6ffe22c05 · outbound

This paper cites Concept steerers: Leveraging k-sparse autoencoders for controllable genera- tions, 2025.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Concept steerers: Leveraging k-sparse autoencoders for controllable genera- tions, 2025

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:13.254187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:05.405466Z digest=sha256:948b0c093ede48a12c7099f3ee06258c31dcb40e7e2a448ea90ca13373e59d81

Observation 24334275-6f37-4872-a995-f2ce66268dd5 · outbound

This paper cites Revelio: Interpreting and leveraging semantic information in diffusion models, 2024.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Revelio: Interpreting and leveraging semantic information in diffusion models, 2024

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:13.079662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:05.485864Z digest=sha256:6b1b30717272d7ac43af17e1add0e629cc3921dbde8ba0585a72f2331fe588ab

Observation e83dbb14-0346-40d0-a3d7-ec4cdbec9fb5 · outbound

This paper cites Bert busters: Outlier dimensions that dis- rupt transformers, 2021.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Bert busters: Outlier dimensions that dis- rupt transformers, 2021

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:12.879563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:05.569734Z digest=sha256:e33f8bfee26b8725f0182d5719682b2c43e94a6b8fa87ce59eb15469034961a4

Observation 71e7c288-b35e-4e7f-b31f-aa28e7125f3c · outbound

This paper cites Instrumenting llm model internals in jax,.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Instrumenting llm model internals in jax,

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:12.707849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:05.666563Z digest=sha256:a5ef5bb52075e1c25e5bf31897013111c1c3b7cc241328a84f4ba977090c3628

Observation 804a9d5c-ec97-4512-acf1-5265d28fa450 · outbound

This paper cites Diffusion models already have a semantic latent space, 2023.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Diffusion models already have a semantic latent space, 2023

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:12.488010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:05.737063Z digest=sha256:df8d4c9122ae181ef84602fe31d42294b97fe124a8b942d2d325ee9fc2a6b39f

Observation 7cfeafe1-efc9-4856-8508-f28ce6495c0e · outbound

This paper cites an unresolved cited work.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Unresolved cited work

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T12:30:05.788150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:30:05.788150Z digest=sha256:7d3ebc44aaad7e06ec1ffe030dbf48184618557f936815f039828d279bf8b914

Observation b69ba8d9-f143-4a13-974d-8d5ead0a01d4 · outbound

This paper cites The remark- able robustness of llms: Stages of inference?, 2024.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning The remark- able robustness of llms: Stages of inference?, 2024

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:12.290413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:05.869828Z digest=sha256:d60949bfec755243acdf4dcd8e2bd2a33c48f0a98f0c44ac02f74f70bfe5c4b1

Observation 9a01235e-b8c4-41b5-b0e7-4b43a850fa71 · outbound

This paper cites Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T12:30:05.981400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:30:05.981400Z digest=sha256:71266a05ca900f8909a78b9f3af08b3d26cc6728a3f4655e2d9dfdd8bdfea17a

Observation 944ce7f2-b77d-4ceb-978b-4c5627924a21 · outbound

This paper cites Sparse crosscoders for cross-layer features and model diff- ing.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Sparse crosscoders for cross-layer features and model diff- ing

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:12.088993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:06.081709Z digest=sha256:4fe0d62ff3115bf1745b6a82746bc4e1be74c958021e386a2b2915547892c09d

Observation 001689a8-169a-4b1a-b1bb-0a1df1090da7 · outbound

This paper cites an unresolved cited work.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Unresolved cited work

Reference 33

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:30:11.911314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:06.172291Z digest=sha256:9f6b35d9595d279d4c58034336c98143cf2af3323ebc29a75c6e0c98dc07b3a8

Observation c174ddcc-dde8-4e74-89ce-5a036071cf9a · outbound

This paper cites Flow straight and fast: Learning to generate and transfer data with rectified flow, 2022.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Flow straight and fast: Learning to generate and transfer data with rectified flow, 2022

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-07T12:30:06.258651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:30:06.258651Z digest=sha256:6535553c976ba455828ad9891729153e461975e0a437bdf44172748c1a60e611

Observation 0d7ee977-6acc-4ecf-9d37-d145218a0d21 · outbound

This paper cites Sparse autoencoder.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Sparse autoencoder

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:11.722682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:06.434565Z digest=sha256:48cc8cdfaf0ade44fd8979010c70fafb85b7ee6609496cedea714467dbcb2599

Observation 20e20cb3-dd12-4cf8-a202-ca35ccca0081 · outbound

This paper cites Shortform comment on sae locality.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Shortform comment on sae locality

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:11.375844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:06.628129Z digest=sha256:1757dd440f7d31c5f29b4d682670615bc05e5bfe000787760ccd158d786ed640

Observation e3c94c30-8f87-4f94-9b83-e192866e6300 · outbound

This paper cites Steering Language Model Refusal with Sparse Autoencoders.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Steering Language Model Refusal with Sparse Autoencoders

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:11.180448Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:06.715545Z digest=sha256:4802b67b2970afece5bc5e5bd16fc7cde6f60448f42a38d80c21110a75a9dd3a

Observation 8fb4fc21-0907-4aa2-a196-051ce875e65f · outbound

This paper cites Unsupervised discovery of semantic latent directions in diffusion models, 2023.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Unsupervised discovery of semantic latent directions in diffusion models, 2023

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:10.994143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:06.798425Z digest=sha256:0ee115598b133de9a6b4bb43445fa5512cb066b162217ba82f6485d4d2b0776a

Observation eb24596d-8444-4710-a3d6-486f656c2f47 · outbound

This paper cites Scalable diffusion models with transformers, 2023.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Scalable diffusion models with transformers, 2023

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-07T12:30:06.916800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:30:06.916800Z digest=sha256:f39fa6c37d6170d16e3edf33f4a0e887a46e48edcece693485c1c14e373e3370

Observation df34ca1e-6272-4e1f-9781-187df0a8001a · outbound

This paper cites Jumping ahead: Improving reconstruction fi- delity with jumprelu sparse autoencoders, 2024.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Jumping ahead: Improving reconstruction fi- delity with jumprelu sparse autoencoders, 2024

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:10.757356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:07.004444Z digest=sha256:e6b6e39471ae2ab67d91803bc79c831ce184a66ebe1c80d099cd782a04562531

Observation 7dcdf20e-b195-447d-9487-44aa28c5e86e · outbound

This paper cites U-net: Convolutional networks for biomedical image segmentation,.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning U-net: Convolutional networks for biomedical image segmentation,

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-07T12:30:07.066929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:30:07.066929Z digest=sha256:a313ae8a599260f6d3680b3d240073060471c3616ab68dd96106eea2f187cfda

Observation 61f51120-868a-42dc-8888-0ef5935a71e6 · outbound

This paper cites Adversarial diffusion distillation, 2023.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Adversarial diffusion distillation, 2023

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-07T12:30:07.215896Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:30:07.215896Z digest=sha256:2d932c6e91e0d183d9468a077152030c5eb844fbd7e8cfc4533fce6996b6cde8

Observation 735008b6-7deb-4038-8638-87c74f50c7b4 · outbound

This paper cites A multimodal automated interpretability agent, 2025.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning A multimodal automated interpretability agent, 2025

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:10.454361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:07.402455Z digest=sha256:3f36dcc55157bd04cd7ff5992eef7404e9a8cd726ba2ac336e7eb274b1602f75

Observation a22edc05-c3a7-4850-b6da-f2d321f8a8b2 · outbound

This paper cites Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-07T12:30:07.561251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:30:07.561251Z digest=sha256:da46f81b68e5e559b016357a4e982c7cfe1d8e12d25d04f06b7bfd506ca3ff62

Observation 5813494f-42d4-449d-a2bc-9ee35df6b3b6 · outbound

This paper cites Taking fea- tures out of superposition with sparse autoencoders.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Taking fea- tures out of superposition with sparse autoencoders

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:10.246680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:07.644009Z digest=sha256:4382861477aa58ae7645f2c3b0388c33a2cc5e5aae4f52a08a64bf09b295bba2

Observation f6b7c4b5-a59d-4408-869b-7dd5280bb70a · outbound

This paper cites Replacing sae encoders with inference-time optimisation, 2024.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Replacing sae encoders with inference-time optimisation, 2024

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:10.080640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:07.732112Z digest=sha256:91f1f3c3367652a37ad02833a2967c0cb1b3f6849ddef9631d6d787783f8dd9f

Observation 4eb423a4-d794-4208-b59a-4044875742f8 · outbound

This paper cites Denois- ing diffusion implicit models.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Denois- ing diffusion implicit models

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:09.939354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:07.835029Z digest=sha256:0086e23fa65464b66a0fcbc34b6c160bc43186d1fa4e38a10e188e0b0119fc12

Observation 7aa851b0-7eab-4b49-b3c5-9ddbe728818f · outbound

This paper cites Unpacking sdxl turbo: Interpreting text-to-image models with sparse au- toencoders, 2024.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Unpacking sdxl turbo: Interpreting text-to-image models with sparse au- toencoders, 2024

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:09.774368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:07.954440Z digest=sha256:258c2831bff41b83e28521fa02099823f7f8b940c6b077aad5593ebc7a4d4cc3

Observation e76d5eb6-34a7-463d-8307-56aa83e7583c · outbound

This paper cites Steering Language Models With Activation Engineering.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Steering Language Models With Activation Engineering

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-07T12:30:08.019779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:30:08.019779Z digest=sha256:e19345237c0ae80f16bee992f11dcce818d5b480b40c77555ddcd1ab06097ac1

Observation b8301b5a-1afa-439b-9feb-ef828fb1da8d · outbound

This paper cites Gomez, Lukasz Kaiser, and Illia Polosukhin.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Gomez, Lukasz Kaiser, and Illia Polosukhin

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:09.616452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:08.109020Z digest=sha256:fabfee7bc45c7fea2b11d8381b7b83f6b3b29d3cc8359ab5fd1478322367cfeb

Observation 2c1edce9-4e66-45c3-9547-74dd8f5a53b2 · outbound

This paper cites A general protocol to probe large vision models for 3d physical understanding, 2024.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning A general protocol to probe large vision models for 3d physical understanding, 2024

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:09.424697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:08.248304Z digest=sha256:3282e524d6281b379f9c1268d2ed09d54f7db103ed7665f96aff90f4c633aedd

Observation 0d1e6d45-2d9c-44e1-9f0f-78b79003553e · outbound

This paper cites Why are adaptive methods good for attention models?,.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Why are adaptive methods good for attention models?,

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:09.219338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:08.319341Z digest=sha256:17d4e51aa5c3a7ea0ef3a9cc0138717a0f289a29c8f6bf985d3c9eea0d907f13

Observation 0147063a-f806-47f9-b3c5-22ce6a029e7d · outbound

This paper cites Adding conditional control to text-to-image diffusion models, 2023.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Adding conditional control to text-to-image diffusion models, 2023

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T12:30:08.968115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:08.427831Z digest=sha256:ef8117d4935c050e6c34a7e5a8a829ec0594e24a65442cd5a45efae674fd625f

Observation 2bfe92c5-e10e-40df-879a-c74a046be0b2 · outbound

This paper cites an unresolved cited work.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Unresolved cited work

Reference 2011

Resolution
unresolved
raw_fallback, observed 2026-08-07T12:30:11.566660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-08-07T12:30:06.518360Z digest=sha256:deeaa55b9776d11c6c6c2b57d78ffde727ef14df8fde1c5c9017669e6e006629

Observation 52a93f41-62af-4a75-ba6c-a3651dc417b8 · outbound

This paper cites an unresolved cited work.

Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning Unresolved cited work

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-07T12:30:03.532808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T12:30:03.532808Z digest=sha256:c4888f1fd87b7f758ea4f0bd82ce1ca7f05b731b961eeb14477e508994b44906

Pith citing papers

Observation c6def9db-e3f4-468f-858e-0c558bb9b20f · inbound

Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers cites this paper.

Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning

Reference 40

Resolution
verified exact
arxiv_id, observed 2026-06-29T07:03:12.642934Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

source=pdf_text observed=2026-06-29T07:03:08.655446Z digest=sha256:653b1b09b26cae310ae7ea584491cb5aa8cbd2fcbdd0187b795a57be8a6bf5f2