INDEX

Explanations

information related to personal and early life details

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

ioxide

-0.64

Ħ¢

-0.56

oug

-0.55

uned

-0.51

valued

-0.49

aye

-0.49

 cheapest

-0.47

ople

-0.47

Ľ

-0.47

casters

-0.47

POSITIVE LOGITS

figure

0.61

 abroad

0.60

wife

0.59

................................................................

0.56

 stint

0.56

nings

0.54

 affairs

0.54

mits

0.53

 overseas

0.53

 indisc

0.52

Activations Density 6.716%

information related to personal and early life details

No Comments

No Known Activations