INDEX

Explanations

sections of text labeled as "Introduction."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

findpost

-0.80

StoryboardSegue

-0.68

[*]

-0.63

argout

-0.62

∴

-0.60

μφωνα

-0.60

ngdoc

-0.57

ismu

-0.55

andidaten

-0.55

 meridional

-0.54

POSITIVE LOGITS

Introduction

1.24

Intro

1.09

 Introduction

1.09

INTRODUCTION

1.07

 INTRODUCTION

1.03

 Intro

1.01

 intro

0.93

intro

0.92

Introducción

0.82

Introdução

0.78

Activations Density 0.061%

sections of text labeled as "Introduction."

No Comments

No Known Activations