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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itars

-0.75

arak

-0.71

ogens

-0.70

agonists

-0.70

 Pharaoh

-0.67

agonist

-0.66

Rak

-0.63

archs

-0.63

tering

-0.63

ching

-0.62

POSITIVE LOGITS

QUI

0.73

aird

0.73

 Louise

0.68

ILA

0.66

otte

0.64

OA

0.64

 jurisd

0.64

FT

0.63

arty

0.62

IX

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.