INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Norn

-0.68

DCS

-0.67

KNOWN

-0.64

 Opportun

-0.63

ãĤ§

-0.63

âĢ¢âĢ¢âĢ¢âĢ¢

-0.63

 Prison

-0.63

 acknowled

-0.62

 queens

-0.61

 Territories

-0.61

POSITIVE LOGITS

SPONSORED

0.92

andr

0.67

notice

0.66

elson

0.64

educ

0.64

mining

0.63

elist

0.62

andro

0.62

arry

0.62

pell

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.