INDEX

Explanations

No Explanations Found

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

utm

-0.82

tesy

-0.73

ieu

-0.67

Ã©s

-0.67

)=(

-0.67

 maternity

-0.67

ayan

-0.65

aching

-0.64

iasm

-0.64

 bicy

-0.63

POSITIVE LOGITS

 ................

0.79

 Spears

0.66

 Despair

0.62

-+-+

0.62

Press

0.61

 Kappa

0.61

 moderator

0.60

inguished

0.59

ZZ

0.59

istani

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.