INDEX

Explanations

nouns related to geographic or structural features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RegressionTest

-0.63

rrggbb

-0.54

webElementGuid

-0.54

aarrggbb

-0.51

EndInit

-0.51

styleType

-0.49

ChildIndex

-0.48

:✨

-0.47

ɵ

-0.46

idemiology

-0.45

POSITIVE LOGITS

 upstairs

0.66

 downstairs

0.63

#!/

0.57

 تضيفلها

0.57

addPreferredGap

0.53

PyExc

0.53

 downtown

0.52

 departament

0.50

addGap

0.50

 ashore

0.50

Activations Density 0.428%

nouns related to geographic or structural features

No Comments

No Known Activations