INDEX

Explanations

empty segments or non-informative text

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

Tokens often followed by prepositions or commas

np_acts-logits-general · gemini-2.0-flash

technical identifiers

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

 dAtA

-0.55

//});

-0.54

//}

-0.53

 ExecuteAsync

-0.53

 uved

-0.52

 normalt

-0.50

-0.48

 vuitton

-0.48

 normally

-0.48

InstanceState

-0.46

POSITIVE LOGITS

bootstrapcdn

0.70

GEBURTSDATUM

0.64

 مشين

0.63

QMetaType

0.62

AntiForgeryToken

0.59

 feather

0.57

ĵo

0.55

OCCURRED

0.54

 resourceCulture

0.54

Зноскі

0.52

Activations Density 0.084%

empty segments or non-informative text

Tokens often followed by prepositions or commas

technical identifiers

No Comments

No Known Activations