INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ãĤ¨ãĥ«

-0.85

alore

-0.74

è£ħ

-0.74

tein

-0.71

 Canterbury

-0.69

abyte

-0.68

 Aber

-0.68

ãĤ´

-0.68

Ö¼

-0.67

iden

-0.66

POSITIVE LOGITS

podcast

0.73

zza

0.72

xp

0.69

flex

0.67

BSD

0.66

fixes

0.66

canon

0.65

wcs

0.64

pora

0.64

archive

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.