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

Reviewer

-0.72

upid

-0.71

fab

-0.71

riots

-0.69

ORY

-0.68

RIP

-0.66

ORN

-0.66

artifacts

-0.64

expr

-0.63

ibling

-0.63

POSITIVE LOGITS

ttle

0.73

ked

0.72

usha

0.67

 Kills

0.64

stal

0.63

idis

0.63

idate

0.62

utenant

0.62

uca

0.62

 Veterinary

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.