INDEX

Explanations

phrases related to instructions, disclaimers, and user engagement prompts

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

Sentences ending with a punctuation mark

np_acts-logits-general · gemini-2.0-flash

characteristic mature

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

ViewImports

-0.85

 tartalomajánló

-0.73

 виправивши

-0.72

Hochspringen

-0.71

 estekak

-0.70

 Мексичка

-0.69



-0.68

styleType

-0.67

apimachinery

-0.67

kloped

-0.66

POSITIVE LOGITS

...

0.65

The

0.62

The

0.56

0.55

0.54

 Verw

0.54

It

0.53

0.52

Get

0.52

0.50

Activations Density 0.262%

phrases related to instructions, disclaimers, and user engagement prompts

Sentences ending with a punctuation mark

characteristic mature

No Comments

No Known Activations