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

 Savior

-0.74

IC

-0.68

 sucker

-0.67

 Sins

-0.66

 Satanic

-0.63

eering

-0.62

 Vander

-0.62

 Powers

-0.62

 Allaah

-0.61

ucer

-0.60

POSITIVE LOGITS

taboola

0.92

league

0.83

inventoryQuantity

0.78

aug

0.74

elight

0.72

nw

0.72

heast

0.71

zona

0.71

culus

0.70

athlon

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.