INDEX

Explanations

phrases related to opinions or statements about people

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

SPONSORED

-0.50

 srfAttach

-0.49

NES

-0.47

SET

-0.47

etric

-0.43

TEXTURE

-0.42

Stud

-0.42

ITAL

-0.42

ital

-0.41

COMPLE

-0.41

POSITIVE LOGITS

 smugglers

0.49

 migrated

0.45

folk

0.43

 hemor

0.43

body

0.43

NetMessage

0.42

 skelet

0.41

 Eater

0.41

 migrate

0.41

 mourning

0.40

Activations Density 12.742%

phrases related to opinions or statements about people

No Comments

No Known Activations