INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

azo

-0.85

aint

-0.74

 bargain

-0.73

azi

-0.73

ERO

-0.71

Spec

-0.68

abolic

-0.68

ovo

-0.68

udder

-0.67

akov

-0.67

POSITIVE LOGITS

çīĪ

0.71

 Merrill

0.67

 colleg

0.66

 Geral

0.65

 buddies

0.64

 marketers

0.63

 linem

0.63

 Karin

0.62

 Likes

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.