INDEX

Explanations

technical terms related to technology and programming

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

cffff

-0.68

ãĥĥãĥī

-0.61

å§«

-0.61

externalActionCode

-0.59

Jr

-0.58

ãĥ´

-0.55

ãĥ³ãĤ¸

-0.53

TAG

-0.53

arty

-0.53

merce

-0.52

POSITIVE LOGITS

ilon

0.50

 Spiel

0.48

orde

0.47

undown

0.47

imov

0.47

ifier

0.47

elines

0.46

ihar

0.46

Wer

0.45

ioxide

0.44

Activations Density 11.564%

technical terms related to technology and programming

No Comments

No Known Activations