INDEX

Explanations

various forms of the word "order" and references to compliance or disobedience related to commands or instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

sidemargin

-0.73

󠁧

-0.68

发表于

-0.67

tvguidetime

-0.67

addContainerGap

-0.64

multer

-0.64

 ostavi

-0.63

存于互联网档案馆

-0.63

 enriquec

-0.62

sharing

-0.61

POSITIVE LOGITS

 instructions

1.15

 orders

1.02

 commands

1.00

 Instructions

1.00

 directives

0.98

 INSTRUCTIONS

0.96

指令

0.95

 Auftrag

0.94

 directive

0.91

 commanded

0.90

Activations Density 0.255%

various forms of the word "order" and references to compliance or disobedience related to commands or instructions

No Comments

No Known Activations