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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cel

-0.67

 Attribution

-0.65

 Cutter

-0.63

 accompan

-0.62

desc

-0.62

alien

-0.61

bear

-0.60

printed

-0.59

requ

-0.59

 insign

-0.58

POSITIVE LOGITS

IUM

0.78

afort

0.73

DragonMagazine

0.70

ovo

0.68

=#

0.67

 antioxid

0.67

)</

0.66

################################

0.64

EngineDebug

0.64

ä½¿

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.