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

taboola

-0.74

@@

-0.67

 Clicker

-0.66

wcsstore

-0.65

NPR

-0.64

 Predators

-0.64

Phones

-0.63

Ń·

-0.63

ãĤ©

-0.62

 Bloomberg

-0.61

POSITIVE LOGITS

eria

0.75

atem

0.72

escription

0.70

alia

0.70

SW

0.66

terness

0.66

ge

0.65

intern

0.65

intend

0.64

edo

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.