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

Mill

-0.80

PART

-0.75

 rall

-0.72

mill

-0.69

éĹĺ

-0.68

BUS

-0.66

Aud

-0.66

Train

-0.65

minist

-0.64

 Train

-0.64

POSITIVE LOGITS

 retract

0.73

vac

0.72

Pwr

0.70

shy

0.66

wel

0.64

 slander

0.63

enses

0.62

 heavyweight

0.61

olkien

0.61

anus

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.