INDEX

Explanations

words and phrases related to homosexuality

oai_token-act-pair · gpt-3.5-turbo

references to homosexuality and related themes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

âĵĺ

-0.81

BuyableInstoreAndOnline

-0.76

Ct

-0.72

Dispatch

-0.68

ç«

-0.68

AZ

-0.68

ADVERTISEMENT

-0.68

 Colo

-0.67

CCC

-0.66

Medic

-0.65

POSITIVE LOGITS

osexual

1.07

xual

1.01

hovah

0.88

bian

0.87

 attracted

0.81

atri

0.77

 pedoph

0.76

 equality

0.76

 homosexuality

0.76

bians

0.75

Activations Density 0.011%

words and phrases related to homosexuality

references to homosexuality and related themes

No Comments

No Known Activations