INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

vana

-0.83

enment

-0.72

anches

-0.72

iddler

-0.70

 legalized

-0.65

enfranch

-0.64

 womb

-0.63

 mathemat

-0.63

 nurturing

-0.62

avement

-0.62

POSITIVE LOGITS

Dat

0.85

py

0.78

ming

0.76

bot

0.73

 Temp

0.70

rite

0.69

Tor

0.67

>]

0.66

________________________________

0.65

TBA

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.