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

orian

-0.74

ı

-0.71

istor

-0.65

fried

-0.63

 Rebellion

-0.63

ozy

-0.63

orians

-0.63

rams

-0.61

 spokes

-0.58

mire

-0.58

POSITIVE LOGITS

antha

0.73

alogue

0.73

externalActionCode

0.70

catentry

0.68

SCP

0.68

itri

0.67

hovah

0.66

ideo

0.65

Delta

0.62

RFC

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.