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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LESS

-0.68

 Messages

-0.65

 TRUE

-0.64

 Meow

-0.64

 Revelations

-0.64

Ø©

-0.64

Bey

-0.64

 Buddy

-0.63

ornia

-0.63

INGTON

-0.63

POSITIVE LOGITS

TI

0.83

hern

0.83

vati

0.81

heng

0.74

ube

0.73

ulia

0.68

atham

0.67

ilt

0.67

agu

0.67

vP

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.