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

»Ĵ

-0.81

 Restore

-0.75

£ı

-0.72

ilus

-0.69

 Refresh

-0.66

 Fill

-0.66

ĳå£«

-0.66

lus

-0.66

Rec

-0.65

ALS

-0.65

POSITIVE LOGITS

xual

0.80

powered

0.73

pire

0.71

abal

0.70

weights

0.67

bid

0.66

ignt

0.65

staking

0.65

rones

0.65

 disadvant

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.