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

Mob

-0.73

iate

-0.73

 hack

-0.72

FTWARE

-0.71

Motor

-0.71

conom

-0.71

È

-0.68

Dat

-0.66

umer

-0.64

SQL

-0.63

POSITIVE LOGITS

asma

0.73

 Chapter

0.73

 Doctors

0.70

osate

0.69

 STAR

0.69

 spoiler

0.68

 Jericho

0.68

 Chapters

0.68

 Newfoundland

0.67

 STATS

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.