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

Ö

-0.71

 itch

-0.68

Occup

-0.68

BILL

-0.68

VK

-0.67

 Seah

-0.67

 Crate

-0.66

=]

-0.66

ANY

-0.63

 Occupy

-0.62

POSITIVE LOGITS

adian

0.83

lighting

0.77

asma

0.73

gers

0.73

hammad

0.71

clerosis

0.71

rowing

0.71

uming

0.70

izontal

0.69

ramids

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.