INDEX

Explanations

phrases related to academic or personal achievements and preferences

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

Follows a question word

np_acts-logits-general · gemini-2.0-flash

most favorite

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

willReturn

-0.55

 שוליים

-0.51

 puissiez

-0.50

Begriffsklä

-0.50

存于互联网档案馆

-0.49

ApiOperation

-0.47

titur

-0.47

Partly

-0.47

$_['

-0.47

 otomatig

-0.47

POSITIVE LOGITS

 favorite

0.90

 favourite

0.87

 Favorite

0.78

 funniest

0.74

 Favourite

0.73

favorite

0.72

 fave

0.72

favourite

0.70

Favorite

0.69

 FAVORITE

0.69

Activations Density 0.205%

phrases related to academic or personal achievements and preferences

Follows a question word

most favorite

No Comments

No Known Activations