INDEX

Explanations

rhetorical questions and expressions of recollection or reflection

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

 esternos

-0.93

tvguidetime

-0.83

 وتسجيلات

-0.83

 autorytatywna

-0.81

 Benth

-0.80

TargetException

-0.78

 myſelf

-0.77

 ویکی‌پدیای

-0.76

 defaultstate

-0.75

 FetchType

-0.75

POSITIVE LOGITS

0.61

ere

0.49

hin

0.48

 تق

0.48

?).

0.47

Zdroje

0.47

kid

0.47

?"

0.47

)?

0.46

"?

0.46

Activations Density 0.123%

rhetorical questions and expressions of recollection or reflection

No Comments

No Known Activations