INDEX

Explanations

terms related to loyalty and dedication in various contexts

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

"loyal" or "loyalty"

np_acts-logits-general · gemini-2.0-flash

loyalty and faithfulness

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Autoritní

-0.57

ChildScrollView

-0.57

enumii

-0.57

-------------</

-0.56

expandindo

-0.54

ItemBackground

-0.54

 nahilalakip

-0.52

 initComponents

-0.51

UnitTesting

-0.50

AnimationsModule

-0.49

POSITIVE LOGITS

 loyal

1.42

 loyalty

1.34

loyal

1.34

 faithful

1.23

 Loyal

1.22

loyalty

1.22

 fidèle

1.17

 Loyalty

1.17

loy

1.16

faithful

1.13

Activations Density 0.176%

terms related to loyalty and dedication in various contexts

"loyal" or "loyalty"

loyalty and faithfulness

No Comments

No Known Activations