INDEX

Explanations

terms associated with mental health, interventions, and educational practices

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

Cognitive or motivational texts

np_acts-logits-general · gemini-2.0-flash

cognitive reframing and motivational interviewing

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

ều

-0.50

достатки

-0.49

LOYEES

-0.49

tais

-0.48

 approved

-0.48

IMENTS

-0.48

 statut

-0.48

 tiens

-0.48

 Chatter

-0.48

ateri

-0.47

POSITIVE LOGITS

uxxxx

0.78

saraba

0.77

 EconPapers

0.72

@[+][

0.69

 isInitialized

0.68

 approach

0.65

 CURIAM

0.65

BASED

0.65

based

0.65

 NUKAT

0.65

Activations Density 0.572%

terms associated with mental health, interventions, and educational practices

Cognitive or motivational texts

cognitive reframing and motivational interviewing

No Comments

No Known Activations