INDEX

Explanations

territorial references, including territorial claims, waters, and disputes

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

 Collider

-0.69

uve

-0.69

book

-0.64

leaf

-0.62

nesota

-0.62

books

-0.62

ollo

-0.61

utical

-0.61

ISTER

-0.61

cone

-0.57

POSITIVE LOGITS

sie

0.70

ity

0.69

 integrity

0.61

raits

0.61

0.58

ication

0.56

 enumer

0.55

inately

0.55

 waters

0.54

ging

0.54

Activations Density 10.220%

territorial references, including territorial claims, waters, and disputes

No Comments

No Known Activations