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

conom

-0.71

erous

-0.68

Ħ¢

-0.66

VIDEO

-0.62

herent

-0.62

cies

-0.60

igmat

-0.60

xiety

-0.59

acular

-0.59

ignt

-0.59

POSITIVE LOGITS

 Flavoring

0.84

ãĤ¢ãĥ«

0.78

Module

0.75

NetMessage

0.72

EVA

0.70

Constructed

0.67

must

0.67

ãĥīãĥ©

0.66

 Releases

0.65

isable

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.