INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

reatment

-0.71

 stride

-0.68

)=(

-0.65

ullah

-0.61

 Phantom

-0.61

Mub

-0.61

utic

-0.56

 EntityItem

-0.55

(*

-0.55

 maiden

-0.54

POSITIVE LOGITS

emale

0.78

ugar

0.74

azon

0.72

IRO

0.72

ACTED

0.71

 Emin

0.67

ple

0.66

 âĸĪ

0.64

itely

0.64

 anonymously

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.