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

 Hanson

-0.77

 Hercules

-0.76

 Blackhawks

-0.70

 Brewers

-0.68

 Ducks

-0.66

 Rampage

-0.64

 Pacers

-0.64

 Hawks

-0.64

rael

-0.63

 Reaction

-0.63

POSITIVE LOGITS

osal

0.79

enko

0.70

arant

0.70

ĸļ

0.69

Reviewed

0.68

ihu

0.67

 Editors

0.66

engineering

0.66

udic

0.65

ogg

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.