INDEX

Explanations

references to self-care and emotional well-being

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

Expressing intentions or deliberate actions

np_acts-logits-general · gemini-2.0-flash

acting with intention

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tagHelperRunner

-0.71

KommentareTeilen

-0.64

Бахар

-0.62

Efq

-0.60

onViewCreated

-0.58

ContentAsync

-0.58

 '\\;'

-0.57

AnimationsModule

-0.57

 مشين

-0.56

 résult

-0.56

POSITIVE LOGITS

 consciously

0.68

 intentional

0.68

 intentionally

0.67

 reminder

0.64

 deliberately

0.61

 remind

0.59

 reminded

0.59

 bewusst

0.58

Remind

0.58

 reminders

0.58

Activations Density 0.205%

references to self-care and emotional well-being

Expressing intentions or deliberate actions

acting with intention

No Comments

No Known Activations