INDEX

Explanations

social media or messaging platform-related terms

oai_token-act-pair · gpt-3.5-turbo

references to popular communication platforms or apps

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

the word "whatsapp"

oai_token-act-pair · gpt-4-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

£ı

-0.85

 COURT

-0.77

¹

-0.75

HCR

-0.74

PIN

-0.74

laws

-0.74

OUS

-0.72

WAYS

-0.71

reau

-0.70

AZ

-0.69

POSITIVE LOGITS

BuyableInstoreAndOnline

0.79

 degraded

0.67

 collapsing

0.65

 degrade

0.64

agara

0.64

chance

0.64

FactoryReloaded

0.64

icing

0.62

 defy

0.59

eri

0.59

Activations Density 0.000%

social media or messaging platform-related terms

references to popular communication platforms or apps

the word "whatsapp"

No Comments

No Known Activations