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

utz

-0.73

é¾įå

-0.65

soDeliveryDate

-0.64

ãĤĭ

-0.64

BUS

-0.63

 LORD

-0.62

 Neph

-0.62

 Graves

-0.61

 YORK

-0.61

EStream

-0.60

POSITIVE LOGITS

iquette

0.86

 reprodu

0.71

isexual

0.70

ateur

0.70

iquid

0.67

anth

0.66

cia

0.66

cart

0.65

ting

0.63

ising

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.