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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 incent

-0.83

inar

-0.77

mercial

-0.75

merce

-0.73

iral

-0.73

olia

-0.71

icable

-0.69

vertisement

-0.69

ajor

-0.66

jri

-0.65

POSITIVE LOGITS

Native

0.75

bilt

0.74

HUD

0.68

Scroll

0.66

Awesome

0.66

Land

0.66

Typ

0.64

wom

0.64

Plex

0.63

Draw

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.