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

ĸļ

-0.83

alogy

-0.68

oday

-0.67

 Rein

-0.66

uate

-0.65

 Chapters

-0.65

ÑĤ

-0.65

Ñģ

-0.65

ifted

-0.63

 Lena

-0.63

POSITIVE LOGITS

 behavi

0.73

 seaw

0.70

ortunately

0.67

quila

0.66

earable

0.64

irgin

0.64

LIA

0.63

 violence

0.63

 Violence

0.63

 rapes

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.