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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

course

-0.83

liga

-0.76

rod

-0.75

artifacts

-0.71

errors

-0.70

window

-0.68

gap

-0.68

gart

-0.67

ties

-0.67

stead

-0.67

POSITIVE LOGITS

EEE

0.72

 Manz

0.71

Rai

0.68

Pai

0.67

 Jeanne

0.67

ENE

0.66

 Leader

0.66

 Cohn

0.65

 Hess

0.65

 Hansen

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.