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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ou

-0.72

 Mechdragon

-0.71

CBC

-0.71

esc

-0.68

WF

-0.66

brook

-0.65

fu

-0.65

 Revival

-0.64

roid

-0.64

advertisement

-0.62

POSITIVE LOGITS

 distingu

0.78

ĺħ

0.73

endment

0.70

ĪĴ

0.68

Dur

0.68

rapnel

0.66

Ö¼

0.66

 grap

0.66

achus

0.64

trak

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.