INDEX

Explanations

phrases indicating comparisons or contrasts

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

followed by commas

np_acts-logits-general · gemini-2.0-flash

respectively, and independence

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

also

-0.91

 meanwhile

-0.78

 dessutom

-0.76

этому

-0.74

 invece

-0.72

 also

-0.70

 portanto

-0.69

Also

-0.68

 hingegen

-0.68

Likewise

-0.66

POSITIVE LOGITS

ViewFeatures

0.73

 المعيارى

0.72

 تضيفلها

0.69

 NUKAT

0.67

 تانيه

0.64

 للمعارف

0.63

Rüyada

0.63

Décès

0.63

 StatefulWidget

0.61

RUnlock

0.60

Activations Density 0.169%

phrases indicating comparisons or contrasts

followed by commas

respectively, and independence

No Comments

No Known Activations