INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

aimon

-0.85

 unpre

-0.74

uds

-0.68

orough

-0.68

soDeliveryDate

-0.67

 discont

-0.64

etermined

-0.63

chance

-0.63

akeru

-0.62

odox

-0.61

POSITIVE LOGITS

UFC

0.75

Russ

0.74

åŃĲ

0.71

INAL

0.70

Ùĩ

0.68

](

0.66

DOC

0.63

––

0.63

0.61

TOR

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.