INDEX

Explanations

references to studies that assess personal experience or contributions

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

prospective study

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 autorytatywna

-0.54

EndInit

-0.50

 كومونز

-0.49

 doInBackground

-0.48

PYX

-0.47

 IndexPath

-0.43

mbic

-0.42

useNewUrlParser

-0.41

forRoot

-0.41

AsUp

-0.40

POSITIVE LOGITS

XmlAccessType

0.62

Izvori

0.57

StoryboardSegue

0.44

Referencer

0.42

Välislingid

0.41



0.41

 يتيمه

0.40

 الرياضيه

0.40

Życiorys

0.39

Enllaços

0.39

Activations Density 0.115%

references to studies that assess personal experience or contributions

prospective study

No Comments

No Known Activations