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

-0.72

 Reboot

-0.72

reach

-0.68

Dur

-0.66

 bragging

-0.65

DJ

-0.64

 tooltip

-0.64

DJs

-0.64

 manifesto

-0.62

agate

-0.62

POSITIVE LOGITS

risome

0.73

occ

0.71

 Toll

0.70

oin

0.69

affer

0.67

alky

0.66

eye

0.65

iencies

0.64

Downloadha

0.63

 Disease

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.