INDEX

Explanations

keywords related to gender identity

oai_token-act-pair · gpt-3.5-turbo

references to gender identity and related issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Lans

-0.76

 Warn

-0.71

baugh

-0.68

Money

-0.68

 rake

-0.67

 Prices

-0.67

 Winc

-0.66

Ing

-0.66

 reinvest

-0.65

 sting

-0.65

POSITIVE LOGITS

 dysph

0.88

iannopoulos

0.84

omas

0.80

 Disorders

0.79

alkyrie

0.78

endered

0.77

ference

0.77

gender

0.76

 disorder

0.76

femin

0.76

Activations Density 0.082%

keywords related to gender identity

references to gender identity and related issues

No Comments

No Known Activations