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

 skelet

-0.79

 tong

-0.76

 downturn

-0.72

ful

-0.69

 snowball

-0.67

 Tasman

-0.66

 diarr

-0.66

 juggling

-0.66

 catapult

-0.65

 cursing

-0.65

POSITIVE LOGITS

ivas

0.85

roma

0.80

etsy

0.76

ussian

0.76

amar

0.75

endor

0.75

alion

0.74

maxwell

0.73

wyn

0.72

icus

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.