INDEX

Explanations

detailed technical terms and descriptions related to specific fields of study and professional practices

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

Afee

-0.55

 Karma

-0.52

Fog

-0.50

ãĥ¼ãĥĨãĤ£

-0.50

DU

-0.50

ãĥ«

-0.49

ãĥ¼ãĥĨ

-0.49

 Petersen

-0.49

Ùĩ

-0.49

 Mistress

-0.48

POSITIVE LOGITS

velength

0.84

anded

0.74

ifted

0.69

odes

0.69

iders

0.69

orrow

0.68

hirt

0.67

overe

0.66

orned

0.66

arious

0.65

Activations Density 6.147%

detailed technical terms and descriptions related to specific fields of study and professional practices

No Comments

No Known Activations