INDEX

Explanations

words indicating control and relationships in a shared context

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

obtaining something

np_acts-logits-general · gemini-2.0-flash

acquiring or reclaiming possessions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.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

 TestBed

-0.68

CloseOperation

-0.67

Šaltiniai

-0.58

PyExc

-0.58

 kaarangay

-0.57

astify

-0.56

 ComVisible

-0.56

 يتيمه

-0.56

sidemargin

-0.55

endpush

-0.54

POSITIVE LOGITS

 resources

0.55

 Prizes

0.54

 undivided

0.53

 ngôi

0.52

 possession

0.52

 loot

0.52

 bragging

0.52

 throne

0.51

 limelight

0.50

 trône

0.50

Activations Density 0.324%

words indicating control and relationships in a shared context

obtaining something

acquiring or reclaiming possessions

No Comments

No Known Activations