INDEX

Explanations

terms related to mental health and its various aspects or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Portale

-0.63

UserScript

-0.53

 minimally

-0.52

ötet

-0.51

ève

-0.50



-0.49

 Valera

-0.48

 Sutton

-0.48

군

-0.48

☆☆

-0.48

POSITIVE LOGITS

ंदीखरीदारी

0.79

 health

0.74

health

0.68

 nahilalakip

0.66

 mental

0.65

 toughness

0.64

 illness

0.64

CloseOperation

0.63

 Health

0.63

دانشنامهٔ

0.62

Activations Density 0.136%

terms related to mental health and its various aspects or conditions

No Comments

No Known Activations