INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Sina

-0.76

Ã¶n

-0.71

hots

-0.70

avorite

-0.68

atoon

-0.68

imoto

-0.68

acus

-0.66

illon

-0.63

ertodd

-0.60

urches

-0.60

POSITIVE LOGITS

ioned

0.79

folk

0.69

 Nadu

0.62

ions

0.61

 Elvis

0.59

 Freeze

0.59

Rue

0.59

rg

0.58

vantage

0.57

groupon

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.