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

RGB

-0.75

FactoryReloaded

-0.72

Recommended

-0.72

rust

-0.72

RAFT

-0.70

isse

-0.68

MK

-0.68

Images

-0.67

Apart

-0.66

Getty

-0.66

POSITIVE LOGITS

 youngest

0.79

 absence

0.76

 heck

0.73

 voic

0.66

 Bahamas

0.65

 elimination

0.64

 Tories

0.64

ueless

0.63

 hardest

0.63

ittal

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.