INDEX

Explanations

references to legal actions, specifically arrests

oai_token-act-pair · gpt-3.5-turbo

instances of the word "arrest" and its variations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÃŁ

-0.81

issance

-0.77

soDeliveryDate

-0.75

emonic

-0.74

vironment

-0.64

 Remastered

-0.63

 tasting

-0.63

merce

-0.62

 deceive

-0.61

^^^^

-0.61

POSITIVE LOGITS

ees

1.15

 Warrant

1.06

 warrants

1.03

 warrant

0.99

able

0.94

ee

0.83

ments

0.80

 arrest

0.80

 affidavit

0.76

 Marshal

0.76

Activations Density 0.047%

references to legal actions, specifically arrests

instances of the word "arrest" and its variations

No Comments

No Known Activations