INDEX

Explanations

references to the Church of Scientology

oai_token-act-pair · gpt-3.5-turbo

mentions of Scientology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Mulcair

-0.76

 Higgins

-0.70

Gaw

-0.70

hower

-0.68

Fir

-0.68

 Ashe

-0.67

LOAD

-0.67

STEM

-0.67

tips

-0.66

Tas

-0.65

POSITIVE LOGITS

onte

0.81

inct

0.78

iatric

0.77

ormal

0.76

World

0.73

 Scientology

0.73

estial

0.72

 Scient

0.72

 Celebrity

0.71

cius

0.71

Activations Density 0.024%

references to the Church of Scientology

mentions of Scientology

No Comments

No Known Activations