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

guards

-0.71

ascript

-0.69

erity

-0.68

 Janeiro

-0.68

 fitt

-0.65

 Cobra

-0.63

gallery

-0.63

angled

-0.62

quartered

-0.61

aped

-0.61

POSITIVE LOGITS

aretz

0.72

doi

0.72

udi

0.72

 è£ıè

0.70

 Mechdragon

0.68

BIT

0.67

Bit

0.67

 Hash

0.66

âĦ¢:

0.66

 Median

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.