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

netflix

-0.89

DragonMagazine

-0.79

 externalToEVAOnly

-0.78

BuyableInstoreAndOnline

-0.73

ãģ®å®

-0.73

PLIED

-0.70

raviolet

-0.67

Downloadha

-0.67

VD

-0.66

 stret

-0.65

POSITIVE LOGITS

 Adin

0.67

 gaping

0.67

 Corinthians

0.65

 eleph

0.63

 anch

0.63

 contributing

0.63

 traced

0.61

 thous

0.61

cur

0.61

 graft

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.