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

alking

-0.77

gression

-0.69

 Morton

-0.66

Jackson

-0.65

 Pompe

-0.65

uca

-0.64

letters

-0.63

 Kinder

-0.62

 Jackson

-0.61

Phill

-0.61

POSITIVE LOGITS

 adren

0.65

stress

0.64

 simulator

0.62

stay

0.60

'';

0.59

shire

0.59

 confir

0.59

 scrut

0.58

?????-

0.58

 colle

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.