INDEX

Explanations

phrases indicating continuation or prompts for further reading

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

جوايز

-0.69

tonode

-0.67

 فريبيس

-0.64

الدراسه

-0.64

 <>",

-0.64

envolvimento

-0.61

 copertina

-0.60

JpaRepository

-0.59

GEBURTSDATUM

-0.58

 ModelExpression

-0.58

POSITIVE LOGITS

devamını

0.69

Weiterlesen

0.68

続きを読む

0.63

 Chien

0.60

<eos>

0.56

weiterlesen

0.55

Tikang

0.54

 مشين

0.54

//}

0.53

❯

0.51

Activations Density 0.127%

phrases indicating continuation or prompts for further reading

No Comments

No Known Activations