INDEX

Explanations

country names

oai_token-act-pair · gpt-3.5-turbo

country names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Horowitz

-0.71

 Vanity

-0.68

 Loft

-0.67

 Breitbart

-0.65

Ped

-0.65

 sidewalk

-0.65

 Sloan

-0.65

 Woodward

-0.65

 Guilty

-0.64

 Eater

-0.64

POSITIVE LOGITS

uania

1.40

 Netherlands

1.37

 Islands

1.25

 Philippines

1.25

Spain

1.23

France

1.20

 Territories

1.19

orea

1.19

 Yugoslavia

1.18

 Argentina

1.17

Activations Density 0.442%

country names

country names

No Comments

No Known Activations