INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

SPONSORED

-1.05

NRS

-0.89

umbai

-0.72

phy

-0.72

Pont

-0.71

Islam

-0.68

AIDS

-0.67

eches

-0.67

ventus

-0.67

icone

-0.65

POSITIVE LOGITS

 Madd

0.70

 Dealer

0.67

ben

0.64

 Madison

0.64

wat

0.62

 widgets

0.62

 Summon

0.62

tool

0.62

 captcha

0.61

 Ship

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.