INDEX

Explanations

terminology related to mental health conditions and stress factors

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

preceding mental health conditions

np_acts-logits-general · gemini-2.0-flash

stress, anxiety, depression, PTSD

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 дописавши

-0.79

 Reverso

-0.73

+#+#

-0.64

OGND

-0.62

 ویکی‌پدی

-0.61

脚注の使い方

-0.54

WebControls

-0.54

 للمعارف

-0.53

 sánh

-0.53

Cec

-0.52

POSITIVE LOGITS

 stress

2.04

 Stress

1.84

stress

1.76

Stress

1.75

 STRESS

1.71

 anxiety

1.52

 stressful

1.51

 stresses

1.41

 stressors

1.40

 stres

1.37

Activations Density 0.475%

terminology related to mental health conditions and stress factors

preceding mental health conditions

stress, anxiety, depression, PTSD

No Comments

No Known Activations