INDEX

Explanations

references to the organization "Judicial Watch"

oai_token-act-pair · gpt-3.5-turbo

mentions of the organization "Judicial Watch."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

istically

-0.76

 flavours

-0.75

 fries

-0.73

wcs

-0.68

isable

-0.67

 toast

-0.67

istic

-0.65

 cure

-0.65

interstitial

-0.65

 oxid

-0.64

POSITIVE LOGITS

dog

1.26

tower

1.17

dogs

1.16

 Watch

0.95

atcher

0.84

 Dogs

0.81

andowski

0.81

 Watching

0.78

point

0.75

wat

0.74

Activations Density 0.024%

references to the organization "Judicial Watch"

mentions of the organization "Judicial Watch."

No Comments

No Known Activations