INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Archdemon

-0.65

 bombard

-0.65

 è£ıç

-0.63

tackle

-0.62

 visiting

-0.62

 Cooke

-0.61

 captcha

-0.60

headers

-0.60

joy

-0.60

 Rampage

-0.59

POSITIVE LOGITS

NK

0.78

 Sorce

0.75

bledon

0.73

mingham

0.72

 perman

0.72

umbledore

0.70

Wr

0.69

 alum

0.69

awaru

0.67

tul

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.