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

DonaldTrump

-0.65

Pad

-0.65

pad

-0.62

ogle

-0.62

 hereby

-0.58

 Xuan

-0.58

Kit

-0.58

padding

-0.57

ydia

-0.56

 Janeiro

-0.56

POSITIVE LOGITS

 horizont

0.76

 Croat

0.67

raints

0.66

etime

0.66

 seiz

0.65

ategory

0.63

arent

0.61

ascript

0.60

stru

0.60

 whine

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.