INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

eers

-0.78

 Header

-0.68

 Wilde

-0.67

breakers

-0.66

 Advertisement

-0.65

 Cheong

-0.62

laughter

-0.62

 Dock

-0.62

 Mouse

-0.61

hander

-0.61

POSITIVE LOGITS

AppData

0.72

atari

0.72

reek

0.70

obil

0.68

natureconservancy

0.65

ione

0.63

 Leban

0.62

oner

0.60

itan

0.60

idas

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.