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

IFrame

Link

Negative Logits

 vandalism

-0.71

Marginal

-0.68

ãģĹ

-0.66

 occup

-0.65

 crow

-0.64

ãģĻ

-0.64

 burg

-0.62

 inmates

-0.61

 burgl

-0.61

 mileage

-0.60

POSITIVE LOGITS

uggest

0.74

ibaba

0.74

ovo

0.74

ifted

0.67

onet

0.66

 Thrust

0.66

irtual

0.66

rongh

0.65

azon

0.65

oneliness

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.