INDEX

Explanations

references to historical events and political figures

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

Values or numbers with equals signs

np_acts-logits-general · gemini-2.0-flash

parenthetical phrases

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

 متعلقه

-0.67

MLLoader

-0.63

 تانيه

-0.57

 cherchés

-0.55

 насељу

-0.53

حياته

-0.53

cellaneous

-0.49

 Familienname

-0.48

raded

-0.46

 louer

-0.46

POSITIVE LOGITS

posedge

0.70

 الاطلاع

0.60

InSection

0.56

Hauptartikel

0.55

rawDesc

0.55

XmlRootElement

0.54

 promedio

0.53

FileDialog

0.52

basicConfig

0.52

 Gesch

0.52

Activations Density 0.584%

references to historical events and political figures

Values or numbers with equals signs

parenthetical phrases

No Comments

No Known Activations