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

ably

-0.67

 bicy

-0.67

 bicycle

-0.67

 sober

-0.67

 restless

-0.65

fox

-0.63

 bicycles

-0.63

 seat

-0.62

job

-0.62

 holidays

-0.61

POSITIVE LOGITS

DragonMagazine

0.85

bourg

0.79

ĸļ

0.75

 Regulation

0.74

ICE

0.73

 Desk

0.71

Newsletter

0.71

Cod

0.70

 Publishers

0.69

 Curve

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.