INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

andra

-0.77

istered

-0.71

xon

-0.70

othy

-0.70

stic

-0.70

AMI

-0.68

kson

-0.67

 Archangel

-0.67

 nuance

-0.66

arian

-0.66

POSITIVE LOGITS

 Tradable

0.80

 Trafford

0.75

ricting

0.72

united

0.71

sbm

0.70

odge

0.66

 checkout

0.66

whel

0.63

 Uniform

0.62

cash

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.