INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

drivers

-0.70

 odds

-0.69

vernment

-0.67

 Edmund

-0.64

 elig

-0.64

vin

-0.64

 Wilmington

-0.64

 Carpenter

-0.64

 rall

-0.63

 Steele

-0.63

POSITIVE LOGITS

Gameplay

0.71

olerance

0.71

 syndrome

0.70

 mindfulness

0.68

anasia

0.68

igm

0.66

andem

0.66

hea

0.65

 pane

0.65

 autism

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.