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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SPONSORED

-0.77

icz

-0.69

Posts

-0.68

ost

-0.67

ore

-0.66

worthiness

-0.65

ADVERTISEMENT

-0.64

oad

-0.63

PAC

-0.63

ause

-0.63

POSITIVE LOGITS

 realise

0.80

DragonMagazine

0.75

 recognise

0.70

inav

0.70

 appreciate

0.68

 realize

0.67

 breathe

0.65

 contemplate

0.64

 cherish

0.63

 celebrate

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.