INDEX

Explanations

technology-related terms, specifically related to software companies and product updates

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

isode

-0.81

 "$:/

-0.75

-0.74

chest

-0.73

interstitial

-0.72

entary

-0.69

indu

-0.69

onies

-0.68

aca

-0.68

cised

-0.68

POSITIVE LOGITS

Ins

0.88

 Stores

0.87

's

0.87

 brass

0.86

 Corporation

0.81

 exec

0.80

 executives

0.79

 employs

0.79

 headquarters

0.78

 spokesperson

0.78

Activations Density 9.724%

technology-related terms, specifically related to software companies and product updates

No Comments

No Known Activations