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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 palp

-0.72

 bladder

-0.71

 erect

-0.70

 Shutterstock

-0.69

reditary

-0.68

imar

-0.67

 dexter

-0.67

 autonom

-0.66

idia

-0.66

illian

-0.66

POSITIVE LOGITS

FO

0.73

 Parables

0.70

hood

0.70

istration

0.65

NOT

0.64

AA

0.64

NJ

0.64

Reviewer

0.63

oops

0.63

Ore

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.