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

 ORDER

-0.78

stanbul

-0.75

ovo

-0.72

eln

-0.66

Reviewed

-0.64

 Order

-0.64

ova

-0.63

Pok

-0.63

 NOTICE

-0.62

ogl

-0.62

POSITIVE LOGITS

sea

0.72

VIDIA

0.72

ounty

0.68

 slic

0.66

icum

0.65

 Garage

0.64

ilities

0.64

ierrez

0.64

 laundry

0.63

Thumbnail

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.