INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 captcha

-0.81

porary

-0.78

ibaba

-0.78

jri

-0.74

isSpecialOrderable

-0.73

igrate

-0.70

 Tsukuyomi

-0.69

aution

-0.67

auga

-0.66

KEY

-0.64

POSITIVE LOGITS

Rare

0.77

 largeDownload

0.68

quest

0.67

Beast

0.66

Train

0.66

acre

0.65

 Planes

0.65

 Tues

0.62

 Rend

0.62

tro

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.