INDEX

Explanations

sentences that indicate research findings or conclusions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ModelExpression

-0.83

IntoConstraints

-0.78

Efq

-0.76

 Anſ

-0.75

 protoimpl

-0.75

astéroïdes

-0.74

 juſt

-0.73

saraba

-0.73

 houſe

-0.72

 Theſe

-0.72

POSITIVE LOGITS

Keywords

0.77

 Keywords

0.69

<eos>

0.66

abstractmethod

0.65

KEYWORDS

0.58

 Abstract

0.55

rez

0.55

Abstract

0.52

 INTRODUCTION

0.50

 keywords

0.50

Activations Density 0.554%

sentences that indicate research findings or conclusions

No Comments

No Known Activations