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

Nev

-0.76

bourg

-0.76

sky

-0.70

LOD

-0.67

KT

-0.67

lund

-0.66

rad

-0.66

ampion

-0.65

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.65

lake

-0.65

POSITIVE LOGITS

 Wonderland

0.70

 Transactions

0.70

TOR

0.68

Cre

0.64

 exch

0.64

 incorpor

0.63

atural

0.63

 Silk

0.62

 transfers

0.61

hess

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.