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

ĸļ

-0.82

 Archdemon

-0.73

 Melvin

-0.69

hran

-0.63

 Cork

-0.61

 Hayden

-0.60

 Jung

-0.60

Ree

-0.59

 Flan

-0.58

 Miller

-0.58

POSITIVE LOGITS

vernment

0.87

ournal

0.85

SpaceEngineers

0.83

amily

0.72

eno

0.68

Ö¼

0.67

amacare

0.67

imates

0.65

merce

0.65

olls

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.