INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Dia

-0.69

 Mour

-0.66

uli

-0.66

Nom

-0.65

assi

-0.63

ixel

-0.63

 Flames

-0.62

ansom

-0.62

ugs

-0.61

omez

-0.61

POSITIVE LOGITS

atio

0.70

################################

0.68

xual

0.64

################

0.63

velt

0.62

 philos

0.61

 bred

0.61

TX

0.61

 endif

0.60

 Tyson

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.