INDEX

Explanations

Slavic language characters in a text, potentially related to language processing or encoding issues

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

isSpecialOrderable

-0.78

ulhu

-0.74

halla

-0.68

inav

-0.68

hani

-0.67

odan

-0.66

kefeller

-0.64

erto

-0.63

anova

-0.62

yip

-0.62

POSITIVE LOGITS

DonaldTrump

0.75

pas

0.75

cÃ©

0.70

cation

0.69

é¾įå

0.63

ãĤ¼

0.63

 Hath

0.62

iors

0.61

duc

0.61

_____

0.59

Activations Density 9.443%

Slavic language characters in a text, potentially related to language processing or encoding issues

No Comments

No Known Activations