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

tsky

-0.70

ike

-0.70

istic

-0.68

llah

-0.67

 rack

-0.64

 shed

-0.64

crete

-0.64

dit

-0.63

 ranc

-0.62

gered

-0.62

POSITIVE LOGITS

————

0.75

BuyableInstoreAndOnline

0.73

soType

0.71

ãĥ´ãĤ¡

0.69

wcsstore

0.68

doi

0.67

Sport

0.66

ãĥ³

0.64

False

0.64

":"/

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.