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

tro

-0.78

Hoy

-0.67

 plotted

-0.63

ussion

-0.62

ModLoader

-0.62

ilogy

-0.62

dk

-0.62

schild

-0.60

enegger

-0.59

sie

-0.58

POSITIVE LOGITS

ggle

0.77

à¼

0.75

ĪĴ

0.68

ãĤ®

0.63

aton

0.63

DEV

0.63

 athlet

0.62

Community

0.62

ciating

0.62

ggles

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.