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

çīĪ

-0.80

ERY

-0.70

 Institution

-0.67

autions

-0.67

 Advertisement

-0.64

isine

-0.63

è¦ļéĨĴ

-0.63

avascript

-0.63

 IMAGES

-0.62

NESS

-0.62

POSITIVE LOGITS

assic

0.78

 breaker

0.70

 dime

0.69

iband

0.69

asio

0.67

undo

0.67

ori

0.66

 fuse

0.65

ezvous

0.65

uum

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.