INDEX

Explanations

phrases related to law enforcement officials and their titles

oai_token-act-pair · gpt-3.5-turbo

titles and roles related to law enforcement and education administration

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

PsyNetMessage

-0.78

-0.75

CET

-0.73

ted

-0.70

plets

-0.67

apore

-0.66

carbon

-0.65

bra

-0.64

British

-0.63

ubuntu

-0.63

POSITIVE LOGITS

 commissioner

0.89

 superintendent

0.87

 Superintendent

0.82

 Lori

0.76

 Marty

0.74

 Stacy

0.74

 Commissioner

0.74

 Shawn

0.72

 examiner

0.70

 district

0.70

Activations Density 0.110%

phrases related to law enforcement officials and their titles

titles and roles related to law enforcement and education administration

No Comments

No Known Activations