INDEX

Explanations

references to user-related entities and authentication in code or data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 initComponents

-0.80

annica

-0.77

#+#

-0.77

blz

-0.70

 Mitter

-0.70

Bli

-0.69

 Rahim

-0.69

CONTENTS

-0.67

ciato

-0.67

 auguri

-0.67

POSITIVE LOGITS

user

0.87

User

0.84

 User

0.82

 USER

0.81

 IUser

0.78

USER

0.78

idUser

0.76

 userSchema

0.76

 GetUser

0.76

 user

0.75

Activations Density 0.049%

references to user-related entities and authentication in code or data structures

No Comments

No Known Activations