INDEX

Explanations

terms related to mental health and well-being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

IsContent

-0.84

 تضيفلها

-0.79

 AssemblyCulture

-0.67

InitVars

-0.63

 AssemblyCompany

-0.62

 Paglinawan

-0.58

Viitteet

-0.58

 démo

-0.57

 nakalista

-0.56

ASM

-0.56

POSITIVE LOGITS

 mental

0.93

 Psyche

0.90

 Mental

0.85

Mental

0.84

 psychological

0.80

Psy

0.79

Psy

0.76

psy

0.76

 emotions

0.76

 PSYCH

0.74

Activations Density 0.311%

terms related to mental health and well-being

No Comments

No Known Activations