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

GAN

-0.67

Tech

-0.67

Poll

-0.67

dayName

-0.66

timer

-0.64

Sun

-0.63

grounds

-0.63

-0.62

Ru

-0.61

Gl

-0.60

POSITIVE LOGITS

ngth

0.81

 Ghostbusters

0.73

rer

0.70

\/\/

0.70

opathic

0.68

opathy

0.67

 explorers

0.66

ursed

0.63

earchers

0.62

arers

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.