INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ician

-0.84

arian

-0.71

arians

-0.68

atton

-0.66

iever

-0.64

wyn

-0.64

iversity

-0.62

owicz

-0.62

bum

-0.62

 Ivanka

-0.62

POSITIVE LOGITS

 Puzzles

0.74

lihood

0.70

 Mysteries

0.67

 illusions

0.66

 resemb

0.65

 à¨

0.65

 Jinn

0.65

 explan

0.63

 Totem

0.62

 elig

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.