INDEX

Explanations

locations of the term "transgender" related to discussions on bathrooms, identity, and legislation

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

BLIC

-0.87

amina

-0.83

iries

-0.80

 Warrant

-0.78

Interstitial

-0.76

 Gerr

-0.75

 Showtime

-0.74

baugh

-0.74

 GOODMAN

-0.74

Office

-0.74

POSITIVE LOGITS

 dysph

1.30

 pronouns

1.01

 Equality

0.99

 identity

0.98

fuck

0.98

 equality

0.97

bender

0.97

 imbalance

0.96

endered

0.95

 stereotypes

0.90

Activations Density 8.488%

locations of the term "transgender" related to discussions on bathrooms, identity, and legislation

No Comments

No Known Activations