INDEX

Explanations

terms related to mental health conditions and treatments

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

Followed by "and" or a comma

np_acts-logits-general · gemini-2.0-flash

circuitry and states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

})*/

-0.36

*/,

-0.34

AutoScale

-0.34

SequentialGroup

-0.33

 '-',

-0.32

⎪

-0.32

、

-0.32

',

-0.32

),(

-0.31

pha

-0.31

POSITIVE LOGITS

 Normdatei

0.69

 ब्रेकडाउन

0.55

and

0.52

SBATCH

0.52

 Administrativna

0.52

 ویکی‌پدی

0.51

queryInterface

0.51

ſelf

0.51

 kaarangay

0.50

AndEndTag

0.49

Activations Density 0.749%

terms related to mental health conditions and treatments

Followed by "and" or a comma

circuitry and states

No Comments

No Known Activations