HejuruUbuyobozi bukurikira
Imashini zidasanzwe zo gukuramo ibintu
Ururimi AI
Ubuyobozi bwa tekiniki
Imodoka zidasanzwe (SAEs) nigikoresho gikurura ibikorwa byimbere byimbere byurusobe rwimitsi mumurongo munini cyane wibintu bisukuye, bisobanurwa nabantu.
Umva iki gitaboAI-byavuzwe · ~2 min
They are one of the leading techniques for opening the 'black box' and seeing what concepts a model actually represents.
Imbere ya transformateur, icyerekezo kimwe cyo gukora ivanga hamwe nibihumbi nibihumbi icyarimwe, bigatuma bigorana gusoma. Autoencoder ni gake ni urusobe ruto rwibice bibiri byatojwe kongera kubaka ibyo bikorwa binyuze murwego rwagutse rwihishe, ariko hamwe nigihano gike gihatira bake gusa muri neuron nyinshi zacyo kurasa icyarimwe. Kubera uwo muvuduko, buri gice cyihishe gikunda kuba umuhanga mubitekerezo bimwe, nka 'kuvuga ikiraro cya Zahabu Zahabu' cyangwa 'code ya Python'. Muri 2024 Anthropic yapimye ibi kuri Claude 3 Sonnet, ikuramo ibintu bigera kuri miriyoni 34, kandi OpenAI na DeepMind byasohoye imirimo ibangikanye SAE. Abashakashatsi barashobora noneho gufunga ikintu hejuru cyangwa hepfo kugirango bagerageze neza icyo ikora.
__AIU_PROTECTED_4 __ 'Irembo rya Zahabu Claude' demo, aho kongera imbaraga imwe ya SAE byatumye icyitegererezo cyerekana ikiraro mubisubizo byose
Gukuramo no gushyira akamenyetso hafi miriyoni 34 ziranga Claude 3 Sonnet kugirango ushushanye amakarita nka sycophancy, amakosa ya code, nimyitwarire idakwiye.
Gushakisha ibintu bijyanye n'umutekano nko kubeshya, kubogama, cyangwa ibintu bishobora guteza akaga bishobora gukurikiranwa cyangwa kuyobora mugihe cyoherejwe
Gukemura impanvu icyitegererezo cyerekana nabi inyongeramusaruro mugusuzuma ibintu bisobanurwa byakorewe mugihe runaka
Tegereza SAEs kuva mumatsiko yubushakashatsi yerekeza kubigenzuzi bifatika no gukoresha ibikoresho byumutekano, harimo imbaho zerekana ibimenyetso biranga ibimenyetso byerekana uburiganya cyangwa umutekano muke. Ibibazo byafunguye birimo 'gutandukanya ibice' (igitekerezo kimwe kigabanyamo byinshi), kubura ibintu, hamwe nigiciro cyamahugurwa SAEs kuri buri cyiciro cyurugero rwimipaka. Icyerekezo gishya nka crosscoders, transcoders, na matryoshka SAEs bigamije gufata ibarwa mubice kandi kuri granularies icyarimwe.
Ibaruwa y'amakuru y'ubuntu
Inkuru eshatu zizewe za AI buri gitondo cy'iminsi y'akazi, zanditse mu rurimi rworoshye. Ubuntu iteka ryose, nta kwamamaza.
Imeri imwe buri munsi y'akazi. Kwiyimura mu buryo bumwe. Ntitwigera tugurisha cyangwa ngo dusangire aderesi yawe.
Isuzume
Ibisubizo ako kanya kuri buri kibazo, n'icyemezo gishobora gusangirwa gifite ID yagenzurwa umaze gutsinda isomo.
Fasha uburezi bwa AI bw'ubuntu. AI Understanding ni umuryango utegamiye kuri leta wa 501(c)(3) — nta kwamamaza, nta kwishyura, iteka ryose. Tanga impano
Imodoka zidasanzwe (SAEs) nigikoresho gikurura ibikorwa byimbere byimbere byurusobe rwimitsi mumurongo munini cyane wibintu bisukuye, bisobanurwa nabantu. Nimwe mubuhanga buyobora mugukingura 'agasanduku kirabura' no kureba icyo icyitegererezo cyerekana.
SAEs yubaka ibikorwa ikoresheje ubugari, buke bwihishe kuburyo ibice bitandukanye bikunda guhuza nibitekerezo byumvikana byabantu.
Sparsity encourages feature-selective activity but does not guarantee perfect one-neuron-per-concept representations.
__AIU_PROTECTED_4 __ '2024' Scaling Monosemanticity 'yakuwe ku rutonde rwa miliyoni 34 ziranga icyitegererezo.
Mugukomeza ibiraro bya Golden Gate Bridge, abashakashatsi bakoze icyitegererezo gikosora ikiraro, berekana ibimenyetso nibitera impamvu, ntabwo ari ibirango gusa.
Abanyamideli bapakira ibintu byinshi mubipimo bigarukira (superposition); birenze, bigari SAE itanga buri cyumba cyicyerekezo kugirango gikore igice cyacyo.
Komeza wige
Abandi bayobozi batoranijwe kuriyi ngingo
HejuruUbuyobozi bukurikira
Imashini zidasanzwe zo gukuramo ibintu
Ururimi AI