INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

rius

-0.77

wolf

-0.77

 Fargo

-0.68

 Ezekiel

-0.68

Shot

-0.66

 Kare

-0.64

BALL

-0.63

lich

-0.62

 Kathleen

-0.62

 sidx

-0.61

POSITIVE LOGITS

igree

0.81

eness

0.73

ippers

0.68

soDeliveryDate

0.68

ignt

0.67

asury

0.66

atcher

0.66

 arrang

0.66

 domains

0.65

PLA

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.