INDEX

Explanations

phrases related to motorcycles and clubs

oai_token-act-pair · gpt-3.5-turbo

topics related to history and clubs or organizations

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

Roe

-0.76

 Tenth

-0.74

 Swan

-0.74

 Singer

-0.72

 Jenner

-0.72

 Shade

-0.72

 Shank

-0.72

 Kahn

-0.69

 Span

-0.68

 Gust

-0.68

POSITIVE LOGITS

1.35

info

1.27

blogspot

1.27

blog

1.24

network

1.20

online

1.18

wordpress

1.17

club

1.15

blogs

1.12

facts

1.12

Activations Density 0.181%

phrases related to motorcycles and clubs

topics related to history and clubs or organizations

No Comments

No Known Activations