INDEX

Explanations

mentions of people's names, specifically the name "Lauren"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Lauren" 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

*/(

-0.78

lication

-0.74

minist

-0.71

ETF

-0.68

Applications

-0.67

icted

-0.66

Downloadha

-0.65

cffffcc

-0.64

drivers

-0.63

 tempered

-0.63

POSITIVE LOGITS

 Lauren

1.20

uren

0.96

Bac

0.85

 Faust

0.81

 Loren

0.79

jen

0.75

ieve

0.74

 Horowitz

0.73

 Laurent

0.73

 Conrad

0.73

Activations Density 0.013%

mentions of people's names, specifically the name "Lauren"

mentions of the name "Lauren" and its variations

No Comments

No Known Activations