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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 referen

-0.70

xual

-0.65

auri

-0.64

 cropped

-0.63

 comma

-0.63

 limb

-0.63

inated

-0.62

 notor

-0.62

civ

-0.62

 VIDEOS

-0.62

POSITIVE LOGITS

 Mehran

0.80

Elsa

0.69

vernight

0.68

\/

0.67

Wah

0.66

ivities

0.63

0.62

âĢİ

0.62

 Fifa

0.61

 Damascus

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.