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

biz

-0.78

interstitial

-0.73

 Xander

-0.70

 Notting

-0.69

 Cosponsors

-0.69

Ń·

-0.69

chens

-0.68

asus

-0.67

 actionGroup

-0.66

cipled

-0.66

POSITIVE LOGITS

lev

0.69

olid

0.67

stim

0.66

 approvals

0.63

Ä±

0.63

 accommodations

0.62

 maps

0.61

opp

0.61

ossier

0.60

 dissatisf

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.