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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iard

-0.77

atz

-0.76

soDeliveryDate

-0.72

Iv

-0.71

adish

-0.71

gio

-0.66

ouver

-0.64

pport

-0.64

xi

-0.64

ussian

-0.64

POSITIVE LOGITS

CHO

0.70

DEF

0.68

 willpower

0.67

HCR

0.63

EMBER

0.62

CHO

0.62

Ļ

0.62

Hero

0.60

joice

0.60

 guts

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.