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

 Harding

-0.76

etheus

-0.68

ide

-0.67

 Badge

-0.66

issy

-0.66

 Mesa

-0.66

ense

-0.65

idas

-0.64

ads

-0.64

assic

-0.63

POSITIVE LOGITS

RFC

0.83

Commission

0.71

 Allaah

0.69

advertisement

0.66

MEP

0.66

 dissatisf

0.65

CLR

0.65

Present

0.64

 Flavoring

0.64

SPONSORED

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.