INDEX

Explanations

phrases related to journalism and storytelling, possibly looking for emotive details and character interactions

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

ILA

-0.68

ĸļ

-0.67

 Printing

-0.65

 Digest

-0.64

 Alert

-0.62

 Donation

-0.61

 Slime

-0.60

 Aging

-0.59

ogenesis

-0.59

 Assessment

-0.59

POSITIVE LOGITS

pees

0.69

 unanswered

0.67

 imaginable

0.67

doms

0.66

grain

0.66

 thousands

0.65

pins

0.65

é»Ĵ

0.64

times

0.64

 headaches

0.64

Activations Density 11.788%

phrases related to journalism and storytelling, possibly looking for emotive details and character interactions

No Comments

No Known Activations