INDEX

Explanations

people's titles or affiliations mentioning organizations or entities

oai_token-act-pair · gpt-3.5-turbo

references to organizations or groups and their leaders

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

animate

-0.63

RIP

-0.62

worldly

-0.60

 ðŁĻĤ

-0.60

Spread

-0.58

Ń·

-0.58

©

-0.56

DragonMagazine

-0.56

icon

-0.54

 fade

-0.54

POSITIVE LOGITS

 told

1.04

 tells

1.03

 wrote

0.98

 testified

0.95

 says

0.95

said

0.94

 explains

0.93

 commented

0.93

told

0.93

 speaks

0.91

Activations Density 0.154%

people's titles or affiliations mentioning organizations or entities

references to organizations or groups and their leaders

No Comments

No Known Activations