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

agnar

-0.87

»Ĵ

-0.85

inav

-0.82

kefeller

-0.79

ihar

-0.74

aptic

-0.73

æĪ¦

-0.71

cyclopedia

-0.70

æ³

-0.70

Eva

-0.69

POSITIVE LOGITS

 smoker

0.68

 loader

0.66

 loophole

0.66

 illegally

0.63

 backlog

0.62

 sufficient

0.62

 fertile

0.62

 partly

0.62

 exclusively

0.61

 unlawfully

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.