INDEX

Explanations

phrases related to completing tasks or actions without certain requirements or hindrances

oai_token-act-pair · gpt-3.5-turbo

phrases indicating the absence of requirements or constraints

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soDeliveryDate

-0.73

estern

-0.71

 largeDownload

-0.69

auri

-0.69

DragonMagazine

-0.65

âĹ¼

-0.64

ASA

-0.63

ERG

-0.62

Draft

-0.60

hement

-0.59

POSITIVE LOGITS

 anymore

1.09

nor

1.03

 beforehand

0.93

 themselves

0.90

 whatsoever

0.87

 oneself

0.85

 slightest

0.83

 necessarily

0.81

})

0.75

 altogether

0.74

Activations Density 0.749%

phrases related to completing tasks or actions without certain requirements or hindrances

phrases indicating the absence of requirements or constraints

No Comments

No Known Activations