INDEX

Explanations

references to cars and vehicles

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

"car"

np_acts-logits-general · gemini-2.0-flash

car insurance and floats

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Gottfried

-0.53

 Blitz

-0.48

yente

-0.47

}),

-0.47

üf

-0.46

adpleegd

-0.46

desta

-0.46

yto

-0.45

-------

-0.45

richt

-0.45

POSITIVE LOGITS

Car

1.48

car

1.47

Car

1.41

car

1.33

 cars

1.27

 Cars

1.27

Cars

1.22

cars

1.21

CAR

1.08

 CARS

1.02

Activations Density 0.143%

references to cars and vehicles

"car"

car insurance and floats

No Comments

No Known Activations

references to cars and vehicles

"car"

car insurance and floats

No Comments

No Known Activations