INDEX

Explanations

phrases related to "ending" something or bringing something to a conclusion

oai_token-act-pair · gpt-3.5-turbo

mentions of government actions or policies related to surveillance and regulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

-0.84

 screenshots

-0.74

 rooft

-0.69

Magikarp

-0.68

 screenshot

-0.67

phot

-0.65

intosh

-0.64

 adjusts

-0.63

tips

-0.61

ighters

-0.60

POSITIVE LOGITS

angering

0.92

 captivity

0.80

clusively

0.79

 pregnancy

0.78

tering

0.78

 residency

0.78

rency

0.77

 pursuit

0.75

 hostilities

0.74

 pregnancies

0.73

Activations Density 0.153%

phrases related to "ending" something or bringing something to a conclusion

mentions of government actions or policies related to surveillance and regulation

No Comments

No Known Activations