INDEX

Explanations

phrases indicating personal perspectives or opinions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

urlpatterns

-0.73

StoryboardSegue

-0.66

 resourceCulture

-0.64

########.

-0.62

PreferredItem

-0.61

Hentet

-0.61

Попис

-0.60

virons

-0.59

Sklici

-0.59

LEGGI

-0.59

POSITIVE LOGITS

ói

0.50

 Hence

0.48

 unknownFields

0.47

 hence

0.46

 explica

0.44

XmlEnum

0.44

idazole

0.44

Maybe

0.43

 كمان

0.42

 OMITBAD

0.42

Activations Density 0.582%

phrases indicating personal perspectives or opinions

No Comments

No Known Activations