INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ãĥ¼ãĥĨãĤ£

-0.76

 sore

-0.69

yout

-0.68

»Ĵ

-0.67

uthor

-0.67

NetMessage

-0.67

 respawn

-0.66

Ĥ¬

-0.65

*/(

-0.64

emon

-0.64

POSITIVE LOGITS

 Temper

0.73

NRS

0.70

Kev

0.63

 Serie

0.61

 Inquisition

0.60

Sob

0.60

La

0.59

Po

0.59

Pag

0.58

 Flores

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.