Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders Article Swipe

PDF

Dong Shu , Xuansheng Wu , Haiyan Zhao , Mengnan Du , Ninghao Liu ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.18653/v1/2025.emnlp-main.87

Related Topics

Criminal Minds: Beyond Borders Season 1

Beyond Paradise (Tv Series)

Beyond The Gates (Tv Series)

Star Trek Beyond

Mad Max Beyond Thunderdome

Beyond The Sea (Black Mirror)

V/H/S/Beyond

Input Device

Beyond The Valley Of The Dolls

Beyond (Band)

Beyond Good & Evil (Video Game)

Far Beyond Driven

Concepts

No concepts available.

Metadata

Type: article
Landing Page: https://doi.org/10.18653/v1/2025.emnlp-main.87
PDF: https://aclanthology.org/2025.emnlp-main.87.pdf
OA Status: gold
OpenAlex ID: https://openalex.org/W4416037078

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4416037078

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.18653/v1/2025.emnlp-main.87

Digital Object Identifier
Title: Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders

Work title
Type: article

OpenAlex work type
Publication year: 2025

Year of publication
Publication date: 2025-01-01

Full publication date if available
Authors: Dong Shu, Xuansheng Wu, Haiyan Zhao, Mengnan Du, Ninghao Liu

List of authors in order
Landing page: https://doi.org/10.18653/v1/2025.emnlp-main.87

Publisher landing page
PDF URL: https://aclanthology.org/2025.emnlp-main.87.pdf

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: gold

Open access status per OpenAlex
OA URL: https://aclanthology.org/2025.emnlp-main.87.pdf

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4416037078
doi	https://doi.org/10.18653/v1/2025.emnlp-main.87
ids.doi	https://doi.org/10.18653/v1/2025.emnlp-main.87
ids.openalex	https://openalex.org/W4416037078
fwci
type	article
title	Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
biblio.issue
biblio.volume
biblio.last_page	1682
biblio.first_page	1673
is_xpac	False
apc_list
apc_paid
language
locations[0].id	doi:10.18653/v1/2025.emnlp-main.87
locations[0].is_oa	True
locations[0].source
locations[0].license	cc-by
locations[0].pdf_url	https://aclanthology.org/2025.emnlp-main.87.pdf
locations[0].version	publishedVersion
locations[0].raw_type	proceedings-article
locations[0].license_id	https://openalex.org/licenses/cc-by
locations[0].is_accepted	True
locations[0].is_published	True
locations[0].raw_source_name	Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
locations[0].landing_page_url	https://doi.org/10.18653/v1/2025.emnlp-main.87
indexed_in	crossref
authorships[0].author.id	https://openalex.org/A5100938790
authorships[0].author.orcid	https://orcid.org/0009-0009-9785-3934
authorships[0].author.display_name	Dong Shu
authorships[0].author_position	first
authorships[0].raw_author_name	Dong Shu
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5089884284
authorships[1].author.orcid	https://orcid.org/0000-0002-7816-7658
authorships[1].author.display_name	Xuansheng Wu
authorships[1].author_position	middle
authorships[1].raw_author_name	Xuansheng Wu
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5102013650
authorships[2].author.orcid
authorships[2].author.display_name	Haiyan Zhao
authorships[2].author_position	middle
authorships[2].raw_author_name	Haiyan Zhao
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5072191151
authorships[3].author.orcid	https://orcid.org/0000-0002-1614-6069
authorships[3].author.display_name	Mengnan Du
authorships[3].author_position	middle
authorships[3].raw_author_name	Mengnan Du
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5007489034
authorships[4].author.orcid	https://orcid.org/0000-0002-9170-2424
authorships[4].author.display_name	Ninghao Liu
authorships[4].author_position	last
authorships[4].raw_author_name	Ninghao Liu
authorships[4].is_corresponding	False
has_content.pdf	True
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://aclanthology.org/2025.emnlp-main.87.pdf
open_access.oa_status	gold
open_access.any_repository_has_fulltext	False
created_date	2025-11-08T00:00:00
display_name	Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
has_fulltext	False
is_retracted	False
updated_date	2025-11-09T23:09:16.995542
primary_topic
cited_by_count	0
locations_count	1
best_oa_location.id	doi:10.18653/v1/2025.emnlp-main.87
best_oa_location.is_oa	True
best_oa_location.source
best_oa_location.license	cc-by
best_oa_location.pdf_url	https://aclanthology.org/2025.emnlp-main.87.pdf
best_oa_location.version	publishedVersion
best_oa_location.raw_type	proceedings-article
best_oa_location.license_id	https://openalex.org/licenses/cc-by
best_oa_location.is_accepted	True
best_oa_location.is_published	True
best_oa_location.raw_source_name	Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
best_oa_location.landing_page_url	https://doi.org/10.18653/v1/2025.emnlp-main.87
primary_location.id	doi:10.18653/v1/2025.emnlp-main.87
primary_location.is_oa	True
primary_location.source
primary_location.license	cc-by
primary_location.pdf_url	https://aclanthology.org/2025.emnlp-main.87.pdf
primary_location.version	publishedVersion
primary_location.raw_type	proceedings-article
primary_location.license_id	https://openalex.org/licenses/cc-by
primary_location.is_accepted	True
primary_location.is_published	True
primary_location.raw_source_name	Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
primary_location.landing_page_url	https://doi.org/10.18653/v1/2025.emnlp-main.87
publication_date	2025-01-01
publication_year	2025
referenced_works_count	0
abstract_inverted_index
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	5
citation_normalized_percentile