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

adobe

-0.83

arians

-0.79

abase

-0.76

lander

-0.72

canon

-0.70

rets

-0.68

arian

-0.67

abo

-0.66

 Asians

-0.65

 Notting

-0.64

POSITIVE LOGITS

enei

0.75

éĩ

0.74

cknowled

0.73

============

0.70

á¸

0.68

========

0.64

======

0.63

ening

0.63

.ãĢį

0.62

OTAL

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.