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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bil

-0.77

ague

-0.61

run

-0.61

 Photos

-0.61

 hires

-0.60

 Vert

-0.60

Mub

-0.60

ALD

-0.58

irgin

-0.57

elight

-0.57

POSITIVE LOGITS

BuyableInstoreAndOnline

0.75

TextColor

0.67

thood

0.66

ļéĨĴ

0.65

xon

0.65

je

0.64

 Fighters

0.63

duction

0.63

gling

0.62

Ingredients

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.