INDEX

Explanations

references to professional roles and achievements

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

awards and recognition

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

новниш

-0.46

 Adams

-0.35

イ

-0.34

maxcdn

-0.34

 anges

-0.34

袈

-0.33

Ged

-0.32

 Thü

-0.31

 ای

-0.31

 Bryson

-0.31

POSITIVE LOGITS

 للمعارف

0.73

 للاسماء

0.70

 kasarigan

0.70

 AssemblyCompany

0.66

Personensuche

0.57

 avoient

0.56

apimachinery

0.56

ftagPool

0.55

 disambiguazione

0.55

 transfieras

0.54

Activations Density 0.025%

references to professional roles and achievements

awards and recognition

No Comments

No Known Activations