INDEX

Explanations

references to specific geographical locations, particularly Columbia and surrounding areas

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

cher

-0.49

olkien

-0.48

idious

-0.48

ugal

-0.47

chers

-0.47

inventory

-0.45

chest

-0.44

ener

-0.44

ched

-0.44

visor

-0.43

POSITIVE LOGITS

 Heights

0.68

 River

0.60

 Pictures

0.58

 Broadcasting

0.57

 Journalism

0.56

 Canal

0.54

 University

0.47

 City

0.47

 Gorge

0.47

 Pike

0.47

Activations Density 7.542%

references to specific geographical locations, particularly Columbia and surrounding areas

No Comments

No Known Activations