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

protected

-0.78

 lockout

-0.77

protection

-0.75

eworks

-0.75

estate

-0.74

aband

-0.71

 obligated

-0.70

cycl

-0.66

secret

-0.65

 protection

-0.65

POSITIVE LOGITS

 Hitchcock

0.80

ieu

0.72

 Sharp

0.69

dar

0.68

 Goff

0.66

Tid

0.65

ciating

0.64

Ã±

0.62

 Stur

0.62

UAL

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.