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

 clicked

-0.78

etheless

-0.72

response

-0.66

phrine

-0.65

endish

-0.65

Connor

-0.64

Ð´

-0.64

colm

-0.63

sten

-0.63

farious

-0.62

POSITIVE LOGITS

CHR

0.77

 Arche

0.72

roo

0.71

 Renaissance

0.66

 Vide

0.65

 Edison

0.64

 Arist

0.64

utton

0.60

 Ribbon

0.60

hod

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.