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

ratom

-0.73

oto

-0.68

ona

-0.67

 cents

-0.66

brook

-0.65

iculty

-0.64

riet

-0.64

raph

-0.63

rose

-0.63

NetMessage

-0.63

POSITIVE LOGITS

 Sutherland

0.69

 Ples

0.68

 PLUS

0.67

huh

0.66

ulkan

0.65

 srfAttach

0.65

 Spock

0.65

alion

0.64

eh

0.64

ie

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.