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

sembly

-0.88

oku

-0.83

ushima

-0.80

ĺħ

-0.78

netflix

-0.76

atom

-0.76

udic

-0.76

INGTON

-0.76

attach

-0.75

achev

-0.73

POSITIVE LOGITS

 Unlock

0.78

 Myth

0.75

 Thief

0.75

 Contracts

0.69

 Hunger

0.69

 Instruments

0.68

 Territories

0.67

 Scenes

0.67

Rs

0.67

 Liter

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.