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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cold

-0.72

 Surge

-0.72

 domestic

-0.68

 Domestic

-0.68

 Bleach

-0.63

 favour

-0.62

 suffice

-0.61

 favor

-0.61

 Doctor

-0.60

 Azerbaijan

-0.60

POSITIVE LOGITS

ignt

0.82

omo

0.80

gha

0.74

HUD

0.73

oya

0.73

endix

0.72

hesda

0.72

onge

0.72

etsk

0.71

apon

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.