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

illet

-0.71

ertodd

-0.69

unia

-0.68

onge

-0.68

 cellul

-0.65

antry

-0.65

ococ

-0.65

nih

-0.64

liv

-0.64

iang

-0.62

POSITIVE LOGITS

Deal

0.65

Roaming

0.64

learn

0.63

IND

0.63

ELY

0.63

WASHINGTON

0.62

Images

0.62

%%

0.61

sheets

0.60

 Proceed

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.