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

ocol

-0.99

awaru

-0.86

ETF

-0.78

assian

-0.77

ivas

-0.75

otic

-0.73

ccording

-0.71

ocratic

-0.71

ocations

-0.71

ricane

-0.70

POSITIVE LOGITS

 Clicker

0.70

 Vide

0.68

 usual

0.67

pel

0.64

bye

0.63

 opener

0.62

 Perez

0.61

backs

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.