INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

atra

-0.79

 Brom

-0.68

zan

-0.68

 rusty

-0.67

alon

-0.66

 amen

-0.65

 Kentucky

-0.64

Kaz

-0.64

Taj

-0.64

 prol

-0.62

POSITIVE LOGITS

è¦ļéĨĴ

0.89

wcs

0.86

ItemImage

0.83

VPN

0.75

netflix

0.74

ItemThumbnailImage

0.71

 Tradable

0.70

ickr

0.70

np

0.69

illusion

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.