INDEX

Explanations

instances of ownership or possession

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

before "owned" or "owns"

np_acts-logits-general · gemini-2.0-flash

owning things

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

+#+

-0.54

triangleq

-0.53

requireNonNull

-0.51

γραφή

-0.50

 remercie

-0.47

 Sitzung

-0.47

SupportActionBar

-0.47

 بيها

-0.47

efeller

-0.46

ongiorno

-0.46

POSITIVE LOGITS

Autoritní

0.80

KommentareTeilen

0.61

 planta

0.58

 small

0.56

 chi̍t

0.53

kuuta

0.52

 venture

0.52

 ventures

0.51

 intptr

0.51

Crítica

0.50

Activations Density 0.199%

instances of ownership or possession

before "owned" or "owns"

owning things

No Comments

No Known Activations