INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Graves

-0.74

 inquest

-0.73

 electors

-0.69

 elector

-0.68

 Commissioner

-0.67

 Colt

-0.66

ĸļ

-0.64

 Conspiracy

-0.63

 Prosecutor

-0.62

 Archdemon

-0.62

POSITIVE LOGITS

ption

0.81

ormon

0.80

oller

0.73

azon

0.72

amins

0.72

estic

0.71

verts

0.70

itiz

0.68

:-)

0.66

usra

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.