INDEX

Explanations

events related to disasters or tragedies involving multiple casualties

oai_token-act-pair · gpt-3.5-turbo

numerical data related to casualties and injuries in violent incidents

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

dayName

-0.85

wcsstore

-0.70

galitarian

-0.65

 CLIENT

-0.63

 univers

-0.62

 perpendicular

-0.62

 Balanced

-0.62

 Millenn

-0.62

 Authent

-0.61

 conformity

-0.61

POSITIVE LOGITS

 wounded

1.32

 injured

1.26

 wounding

1.22

 injuring

1.11

 injure

1.05

 hospitalized

1.03

 injuries

0.92

 others

0.88

 survivors

0.85

 critically

0.83

Activations Density 0.220%

events related to disasters or tragedies involving multiple casualties

numerical data related to casualties and injuries in violent incidents

No Comments

No Known Activations