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

shore

-0.83

crew

-0.77

boarding

-0.70

eworks

-0.69

 Emails

-0.69

ework

-0.68

guards

-0.68

paio

-0.66

 entry

-0.65

boss

-0.65

POSITIVE LOGITS

 pige

0.76

ali

0.74

POSE

0.73

 mosqu

0.72

 immortality

0.67

 Communism

0.66

 Everywhere

0.66

galitarian

0.65

 Reprodu

0.65

 Atom

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.