INDEX

Explanations

references to political structures and historical governance

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

Occurrences involving numbers or sequences

np_acts-logits-general · gemini-2.0-flash

counting successive items

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

Sklici

-0.59

 tonight

-0.57

昨晚

-0.55

DIPSETTING

-0.55

Yesterday

-0.55

ktop

-0.55

MockBean

-0.54

 Yesterday

-0.54

 scoper

-0.54

 todav

-0.54

POSITIVE LOGITS

 successive

0.88

 annual

0.82

 generations

0.75

decade

0.75

 yearly

0.75

 years

0.73

 presidents

0.71

出版年

0.71

 decades

0.70

 consecutive

0.67

Activations Density 0.360%

references to political structures and historical governance

Occurrences involving numbers or sequences

counting successive items

No Comments

No Known Activations