INDEX

Explanations

phrases or sentences describing instances of people getting wounded or injured

oai_token-act-pair · gpt-3.5-turbo

references to injuries and casualties in contexts involving violence or disasters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

perm

-0.78

SpaceEngineers

-0.76

istries

-0.74

gency

-0.67

tz

-0.67

soDeliveryDate

-0.66

ramid

-0.66

etics

-0.66

ãĥ¼ãĥĨãĤ£

-0.65

etic

-0.64

POSITIVE LOGITS

jured

0.83

 bystanders

0.80

lehem

0.77

lyak

0.72

Oro

0.71

 wounding

0.69

 wounded

0.64

bay

0.64

 Survivors

0.63

 responders

0.62

Activations Density 0.037%

phrases or sentences describing instances of people getting wounded or injured

references to injuries and casualties in contexts involving violence or disasters

No Comments

No Known Activations