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

 commute

-0.72

Reviewer

-0.68

ulton

-0.67

jog

-0.67

VIDIA

-0.66

 mysteriously

-0.66

 elephants

-0.64

iflower

-0.64

atorium

-0.63

 trains

-0.62

POSITIVE LOGITS

 Bulg

0.76

 CONFIG

0.72

0.69

BuyableInstoreAndOnline

0.69

 CentOS

0.69

eller

0.69

 Kinnikuman

0.67

AZ

0.65

 Instruments

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.