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

 Holiday

-0.71

RFC

-0.67

HOME

-0.65

 toxin

-0.64

 Contracts

-0.63

BALL

-0.63

 Happiness

-0.62

 Recipes

-0.62

¥µ

-0.62

 alcoholic

-0.62

POSITIVE LOGITS

theless

0.81

ength

0.75

\":

0.73

abwe

0.72

PsyNetMessage

0.72

 scrut

0.71

issy

0.69

auer

0.69

igenous

0.69

 conclud

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.