INDEX

Explanations

references to the Canadian Prime Minister, Justin Trudeau

oai_token-act-pair · gpt-3.5-turbo

references to Justin Trudeau

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bler

-0.83

gran

-0.75

oxide

-0.73

Ö¼

-0.73

âĵĺ

-0.73

-0.72

×Ļ

-0.70

iHUD

-0.67

stract

-0.65

Reviewer

-0.65

POSITIVE LOGITS

udeau

1.22

 Trudeau

1.10

 Jinping

0.80

bourg

0.79

itÃ©

0.78

isms

0.76

 Liberals

0.76

ism

0.75

utan

0.74

 ministerial

0.72

Activations Density 0.011%

references to the Canadian Prime Minister, Justin Trudeau

references to Justin Trudeau

No Comments

No Known Activations