INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

roman

-0.67

 Jude

-0.65

timer

-0.65

RS

-0.64

ä½¿

-0.63

 illum

-0.63

idian

-0.62

itor

-0.61

èĢ

-0.60

obi

-0.60

POSITIVE LOGITS

Kids

0.82

igers

0.79

uckland

0.78

aughs

0.74

hent

0.73

arie

0.72

artisan

0.72

Seattle

0.70

 compr

0.69

EStream

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.