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

agos

-0.77

 preced

-0.68

includes

-0.64

achus

-0.62

 Crusher

-0.62

 Leia

-0.61

tis

-0.61

osterone

-0.61

jiang

-0.59

Carter

-0.59

POSITIVE LOGITS

 opio

0.72

Ħ¢

0.68

 artif

0.67

 metab

0.66

 rall

0.66

ominated

0.65

ethe

0.64

mble

0.63

GoldMagikarp

0.63

duction

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.