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

worm

-0.78

epad

-0.76

igible

-0.74

xual

-0.70

 assum

-0.67

âĶģ

-0.67

uce

-0.67

å¥³

-0.66

yout

-0.66

plane

-0.66

POSITIVE LOGITS

 Blooming

0.76

 Roberts

0.67

ISTORY

0.66

 Kendall

0.66

iris

0.65

 Gale

0.63

ober

0.62

 Journal

0.61

rift

0.61

ret

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.