INDEX

Explanations

phrases related to achievements and recognition, particularly in media and politics

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

orth

-0.82

ocument

-0.79

eele

-0.76

ItemTracker

-0.74

akeru

-0.73

Äĩ

-0.73

iliary

-0.70

iscopal

-0.70

ulator

-0.67

ocus

-0.66

POSITIVE LOGITS

 weeds

0.86

 unfocusedRange

0.80

 hall

0.72

 dumps

0.70

 creek

0.69

 rabbit

0.69

 hallway

0.67

 ashes

0.67

dden

0.66

graded

0.65

Activations Density 1.166%

phrases related to achievements and recognition, particularly in media and politics

No Comments

No Known Activations