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

ĪĴ

-0.88

İĭ

-0.79

Ľ

-0.75

sylvania

-0.69

į

-0.67

Ŀ

-0.64

Ĭ±

-0.63

Ĥİ

-0.63

 Ending

-0.63

Ĵ

-0.62

POSITIVE LOGITS

rave

0.70

ausible

0.65

uder

0.65

gross

0.63

',

0.63

achev

0.63

annis

0.62

acht

0.61

asking

0.61

 Printed

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.