INDEX

Explanations

phrases indicating capability or preparedness

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

preceding "position" or related terms

np_acts-logits-general · gemini-2.0-flash

in a position to do

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 MainAxisSize

-0.71

 Италијани

-0.63

 jScrollPane

-0.55

webElementXpaths

-0.54

RegressionTest

-0.54

 Paglinawan

-0.52

WriteBarrier

-0.52

'{@

-0.52

tagHelperRunner

-0.51

 ExecuteAsync

-0.51

POSITIVE LOGITS

 equipped

1.28

 ready

1.16

 prepared

1.16

 equip

1.02

equipped

1.02

 preparedness

0.99

 unprepared

0.99

prepared

0.99

ready

0.98

 Equipped

0.96

Activations Density 0.202%

phrases indicating capability or preparedness

preceding "position" or related terms

in a position to do

No Comments

No Known Activations