INDEX

Explanations

locations associated with tragic events or atrocities

oai_token-act-pair · gpt-3.5-turbo

references to significant incidents or events, particularly mass shootings

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

natureconservancy

-0.81

minist

-0.80

lot

-0.76

BILITIES

-0.76

sers

-0.75

linger

-0.72

NOW

-0.71

HAEL

-0.71

Position

-0.70

é¾įå¥ĳå£«

-0.68

POSITIVE LOGITS

 Ukraine

1.03

humane

1.01

 Yugoslavia

1.00

effic

0.96

 Yemen

0.94

 Libya

0.91

efficiency

0.90

 conjunction

0.90

 Catalonia

0.90

 Syria

0.90

Activations Density 0.220%

locations associated with tragic events or atrocities

references to significant incidents or events, particularly mass shootings

No Comments

No Known Activations