INDEX

Explanations

mentions of the word "My" followed by a proper noun

oai_token-act-pair · gpt-3.5-turbo

references to specific media titles or franchises

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 bott

-0.79

ooz

-0.73

 yourselves

-0.69

 forcefully

-0.68

inelli

-0.62

 wisely

-0.62

igham

-0.62

 characterized

-0.62

ieri

-0.62

 ramps

-0.62

POSITIVE LOGITS

stery

1.63

riad

1.53

anmar

1.40

stic

1.33

ths

1.26

chal

1.12

ocard

1.12

ster

1.10

croft

1.08

Space

1.02

Activations Density 0.048%

mentions of the word "My" followed by a proper noun

references to specific media titles or franchises

No Comments

No Known Activations