INDEX

Explanations

mentions of organizations or groups with the word "Citizens" in their name

oai_token-act-pair · gpt-3.5-turbo

references to the term "Citizens" and variations of it

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

efully

-0.88

eful

-0.79

eway

-0.72

urst

-0.72

bed

-0.69

ftime

-0.68

mers

-0.68

ugal

-0.67

aul

-0.66

ery

-0.66

POSITIVE LOGITS

 Citizens

0.90

itizens

0.83

ortium

0.81

 Advice

0.78

 Citizen

0.76

 Against

0.74

 Eagle

0.69

 Lounge

0.69

 Council

0.69

 Clicker

0.67

Activations Density 0.019%

mentions of organizations or groups with the word "Citizens" in their name

references to the term "Citizens" and variations of it

No Comments

No Known Activations