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

Topic

-0.76

 SIGN

-0.74

Growing

-0.73

 Sabha

-0.70

OUR

-0.68

++++++++++++++++

-0.66

 Labrador

-0.66

Sexual

-0.65

cca

-0.63

Austral

-0.63

POSITIVE LOGITS

bats

0.80

ichen

0.74

yrus

0.73

 disclaim

0.69

edIn

0.67

pse

0.66

 forfe

0.63

 contingency

0.63

 reserves

0.62

 contestants

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.