INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

SPONSORED

-0.83

uria

-0.72

ebin

-0.70

advertisement

-0.70

)].

-0.69

 possessions

-0.68

 sails

-0.66

iggurat

-0.66

football

-0.65

ursed

-0.65

POSITIVE LOGITS

"@

0.79

actionDate

0.74

 Synd

0.70

ople

0.69

cdn

0.69

erential

0.69

 Advis

0.64

lington

0.62

 Nieto

0.61

 Dear

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.