INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

pen

-0.74

SY

-0.73

antry

-0.73

Pen

-0.70

inia

-0.68

DI

-0.67

iciary

-0.67

iframe

-0.66

berra

-0.66

zik

-0.64

POSITIVE LOGITS

Ĥİ

0.73

 drowned

0.68

 Santana

0.67

 Rookie

0.66

irez

0.65

Winged

0.63

 Sergey

0.63

 Mulcair

0.63

 Accessed

0.62

 Morales

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.