INDEX

Explanations

phrases related to individuals openly identifying with their sexual orientation or political beliefs

oai_token-act-pair · gpt-3.5-turbo

instances of the word "openly" in a variety of contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Summoner

-0.74

nesota

-0.72

akeru

-0.71

anan

-0.67

ramid

-0.66

eer

-0.65

 Karma

-0.65

Guy

-0.65

wich

-0.63

oooo

-0.62

POSITIVE LOGITS

odox

0.83

obin

0.79

 openly

0.77

lit

0.75

 confess

0.71

 contradicted

0.71

 defied

0.71

lishing

0.71

 disreg

0.71

 expressed

0.70

Activations Density 0.014%

phrases related to individuals openly identifying with their sexual orientation or political beliefs

instances of the word "openly" in a variety of contexts

No Comments

No Known Activations