INDEX

Explanations

names of individuals and specific entities mentioned 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

manship

-0.54

smanship

-0.54

MpServer

-0.54

alach

-0.54

fman

-0.52

flies

-0.51

orc

-0.51

INESS

-0.51

soDeliveryDate

-0.49

eer

-0.49

POSITIVE LOGITS

 Horton

0.65

 Farage

0.64

 Ricardo

0.58

 Nigel

0.49

 Pearce

0.49

Ray

0.48

 Trent

0.46

 Brune

0.46

 Cole

0.45

 Mald

0.45

Activations Density 10.025%

names of individuals and specific entities mentioned in a text

No Comments

No Known Activations