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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

artz

-0.78

retty

-0.73

ãģ«

-0.72

oop

-0.69

éĸ

-0.68

allo

-0.68

Ô

-0.66

ailand

-0.66

aeda

-0.66

igs

-0.65

POSITIVE LOGITS

 dementia

0.78

Merit

0.63

 rejuven

0.62

 raven

0.62

 juven

0.61

 Ukip

0.61

 Commun

0.60

 Meditation

0.60

 fundament

0.60

 Venom

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.