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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EStreamFrame

-0.82

ATA

-0.74

ACY

-0.73

asta

-0.68

seless

-0.68

Secret

-0.67

axter

-0.66

hp

-0.62

umber

-0.62

 Unlock

-0.60

POSITIVE LOGITS

ãĥĥãĥī

0.80

ãĤ¡

0.70

 deficiencies

0.70

 Patriarch

0.69

itect

0.68

ãĤ©

0.67

agna

0.65

 deployments

0.63

 Conversion

0.62

 Extensions

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.