INDEX

Explanations

phrases related to mental health awareness and support

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

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

 للاسماء

-0.70

 ModelExpression

-0.67

 متعلقه

-0.60

vode

-0.59

 handleMessage

-0.56

 StatelessWidget

-0.55

 OnInit

-0.54

 betweenstory

-0.54

Filmographie

-0.54

Abit

-0.53

POSITIVE LOGITS

 entire

0.87

 overall

0.85

 broader

0.81

 wider

0.77

整个

0.74

 whole

0.74

overall

0.70

整個

0.69

 ogóle

0.68

entire

0.68

Activations Density 0.353%

phrases related to mental health awareness and support

No Comments

No Known Activations