INDEX

Explanations

terms related to mental health

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

"Mental" followed by "health"

np_acts-logits-general · gemini-2.0-flash

mental health and wellbeing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 AssemblyCulture

-0.60

UserScript

-0.58

Portale

-0.58

(;;)

-0.56

NavController

-0.56

пуль

-0.55

 通販

-0.55

друг

-0.55

 referrerpolicy

-0.54

Portail

-0.54

POSITIVE LOGITS

 health

0.94

health

0.80

 Health

0.78

 mental

0.76

 Mental

0.75

 HEALTH

0.69

ंदीखरीदारी

0.69

Mental

0.67

Health

0.67

 illness

0.66

Activations Density 0.076%

terms related to mental health

"Mental" followed by "health"

mental health and wellbeing

No Comments

No Known Activations