INDEX

Explanations

references to timeframes and dates

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

years and months

np_acts-logits-general · gemini-2.0-flash

date ranges and years

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

 ویکی‌پدیای

-0.78

rungsseite

-0.77

 مشين

-0.75

Obrázky

-0.72

 oprot

-0.71

 NSCoder

-0.69

 iprot

-0.69

 CURIAM

-0.69

RTSC

-0.69

клопе

-0.68

POSITIVE LOGITS

 năm

1.50

 vuonna

1.45

 tahun

1.39

 January

1.39

 December

1.34

 February

1.33

 בשנת

1.33

 November

1.32

 September

1.27

 October

1.27

Activations Density 2.156%

references to timeframes and dates

years and months

date ranges and years

No Comments

No Known Activations