INDEX

Explanations

technical terms and explanations in a text

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

Downloadha

-0.91

 allegedly

-0.69

 supposedly

-0.67

 plagued

-0.57

 guiActiveUnfocused

-0.56

 purportedly

-0.55

 respectively

-0.54

 reportedly

-0.53

ullah

-0.52

 invariably

-0.52

POSITIVE LOGITS

 myself

1.05

 ourselves

0.97

poke

0.80

 somew

0.79

ulate

0.76

 ASAP

0.74

ayne

0.71

 somet

0.69

uate

0.67

 oneself

0.67

Activations Density 13.311%

technical terms and explanations in a text

No Comments

No Known Activations