INDEX

Explanations

terms related to opposition or criticism against specific groups or ideologies

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

 Halls

-0.93

ãĤ¼ãĤ¦ãĤ¹

-0.89

ĸļ

-0.86

 Pelicans

-0.85

ODY

-0.85

shire

-0.85

hower

-0.80

 Lawn

-0.76

hetti

-0.76

 COUNTY

-0.76

POSITIVE LOGITS

abortion

1.29

war

1.27

establishment

1.25

hero

1.09

anti

1.06

jud

1.01

overty

1.00

measures

1.00

strate

0.99

-'

0.98

Activations Density 4.631%

terms related to opposition or criticism against specific groups or ideologies

No Comments

No Known Activations