INDEX

Explanations

connections to influential entities or individuals

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

Prepositions

np_acts-logits-general · gemini-2.0-flash

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

ChildScrollView

-0.54

 demás

-0.49

 suivants

-0.43

 lainnya

-0.43

etc

-0.43

 suivantes

-0.42

 lisäksi

-0.42

Others

-0.41

 kautta

-0.41

 recueil

-0.40

POSITIVE LOGITS

 kasarigan

0.71

the

0.63

$_(

0.62

+#+

0.60

@[

0.59

localVar

0.57

 AssemblyCompany

0.57

 EconPapers

0.57

 transférez

0.56

CppMethod

0.55

Activations Density 0.655%

connections to influential entities or individuals

Prepositions

No Comments

No Known Activations