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

 Calder

-0.70

acas

-0.69

urat

-0.63

antam

-0.62

 Compan

-0.61

 Vegas

-0.58

 Dancing

-0.57

 Kindle

-0.56

 Tucson

-0.56

teenth

-0.55

POSITIVE LOGITS

we

1.47

_>

0.73

feld

0.71

uke

0.68

azer

0.66

pan

0.66

fl

0.65

rog

0.65

rex

0.65

omsky

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.