INDEX

Explanations

temporal markers or indicators related to time-sensitive events

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

 متعلقه

-0.71

存于互联网档案馆

-0.67

rungsseite

-0.64

énario

-0.63

oneofs

-0.63

يميديا

-0.63

 tslint

-0.62

 myſelf

-0.61

 zirc

-0.60

 saites

-0.60

POSITIVE LOGITS

 after

0.94

 before

0.78

after

0.78

 beginning

0.74

 после

0.73

 AFTER

0.73

After

0.68

 After

0.68

 final

0.66

 dopo

0.66

Activations Density 0.602%

temporal markers or indicators related to time-sensitive events

No Comments

No Known Activations