INDEX

Explanations

automotive brands and models, specifically related to vehicle specifications and recalls

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

Barracuda, Cuda, codes

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

BMW

-0.51

KTM

-0.48

 Ford

-0.46

 Volkswagen

-0.45

ennheiser

-0.45

BMW

-0.45

KTM

-0.45

 Porsche

-0.44

Mustang

-0.43

 ActionResult

-0.43

POSITIVE LOGITS

protoimpl

0.51

 vectorielle

0.51

 féd

0.48

 Италијани

0.47

GEBURTSDATUM

0.46

存于互联网档案馆

0.44

exitRule

0.43

 vectorielles

0.43

 strictement

0.41

 universelle

0.39

Activations Density 0.032%

automotive brands and models, specifically related to vehicle specifications and recalls

Barracuda, Cuda, codes

No Comments

No Known Activations