INDEX

Explanations

contexts involving authority and decision-making

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

foreign words and phrases

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

ContentAsync

-0.60

WireFormatLite

-0.59

oredCriteria

-0.57

 AssemblyCulture

-0.56

 Roskov

-0.54

 ExecuteAsync

-0.52

GEBURTSDATUM

-0.52

plish

-0.50

 actionMode

-0.50

SharedCtor

-0.49

POSITIVE LOGITS

 faibles

0.36

 montanha

0.36

AutoField

0.34

 kontroll

0.33

 debole

0.33

Uwagi

0.33

 dégâts

0.33

 Keuangan

0.32

 farlo

0.32

 Sonn

0.32

Activations Density 0.159%

contexts involving authority and decision-making

foreign words and phrases

No Comments

No Known Activations