INDEX

Explanations

references to receiving news updates, promotions, and newsletters from The New York Times

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

abase

-0.66

ello

-0.61

onics

-0.61

uca

-0.60

aimon

-0.59

okane

-0.58

undown

-0.56

 appell

-0.55

terday

-0.54

oshop

-0.53

POSITIVE LOGITS

APD

0.65

});

0.62

earable

0.60

Article

0.60

govtrack

0.58

 Terms

0.57

 trave

0.56

isodes

0.53

 Gutenberg

0.52

 Caller

0.51

Activations Density 4.843%

references to receiving news updates, promotions, and newsletters from The New York Times

No Comments

No Known Activations