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

awaru

-0.85

 recip

-0.73

 dissatisf

-0.73

untarily

-0.72

 challeng

-0.72

ilaterally

-0.68

uben

-0.68

ajor

-0.67

 plaint

-0.67

seek

-0.67

POSITIVE LOGITS

 Testing

0.65

onso

0.65

vet

0.63

 Rated

0.62

 Lamar

0.61

 Riders

0.61

é¾įå

0.60

 Mobility

0.60

Ti

0.60

DEN

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.