INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

=]

-0.81

 cort

-0.68

 Acer

-0.66

Cy

-0.66

][

-0.65

Alc

-0.63

AMD

-0.63

 hormonal

-0.62

 opio

-0.62

 antioxid

-0.62

POSITIVE LOGITS

ãĥ¼ãĥĨãĤ£

0.78

tesy

0.74

ortium

0.73

iture

0.73

ATTLE

0.72

itu

0.70

gotten

0.70

endor

0.69

enberg

0.68

ARS

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.