INDEX

Explanations

proper nouns and names in the text, such as people's names and locations

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

å£«

-0.72

ounter

-0.62

tesy

-0.61

NetMessage

-0.60

ccording

-0.57

 captcha

-0.56

angan

-0.55

cies

-0.54

ESSION

-0.53

zzo

-0.53

POSITIVE LOGITS

geist

0.85

 Zeit

0.71

bugs

0.62

bug

0.61

 Spiegel

0.60

lon

0.60

feld

0.59

Neh

0.57

 Wings

0.57

lab

0.56

Activations Density 6.408%

proper nouns and names in the text, such as people's names and locations

No Comments

No Known Activations