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

imb

-0.78

pine

-0.77

Michigan

-0.75

Cour

-0.75

Madison

-0.65

gars

-0.65

keyes

-0.65

strap

-0.65

Wisconsin

-0.64

Georgia

-0.64

POSITIVE LOGITS

 reserv

0.67

 sourcing

0.66

ulhu

0.65

 regeneration

0.62

 scouting

0.61

 rounding

0.61

 operating

0.59

 concentrating

0.59

 detecting

0.59

 WARRANT

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.