INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

laus

-0.70

odox

-0.67

ricanes

-0.67

Jr

-0.66

Jr

-0.66

olicy

-0.65

ulty

-0.64

bench

-0.63

 Droid

-0.63

enegger

-0.63

POSITIVE LOGITS

oday

0.72

 apologise

0.68

£ı

0.66

ļéĨĴ

0.63

igm

0.62

ivable

0.62

yip

0.62

 breathe

0.62

 rehe

0.61

 forged

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.