INDEX

Explanations

phrases related to embracing or accepting something

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

akov

-0.52

opers

-0.50

cano

-0.48

hiba

-0.48

iasis

-0.47

ammy

-0.47

arcity

-0.47

©¶æ¥µ

-0.46

cards

-0.46

etry

-0.46

POSITIVE LOGITS

 embrace

0.56

prise

0.54

 uncond

0.53

nesday

0.52

glers

0.50

 embraces

0.49

tails

0.49

edIn

0.48

aneers

0.48

ffee

0.48

Activations Density 10.409%

phrases related to embracing or accepting something

No Comments

No Known Activations