INDEX

Explanations

references to digital concepts and their implications in technology

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

followed by time periods

np_acts-logits-general · gemini-2.0-flash

long ago

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

ValueStyle

-0.78

 InputDecoration

-0.71

原始内容存档于

-0.71

HtmlAttribute

-0.69

ORAGE

-0.66

ModelAdmin

-0.61

ViewInit

-0.59

URLException

-0.58

mockMvc

-0.57

EClass

-0.54

POSITIVE LOGITS

 years

1.76

 earlier

1.69

 hace

1.45

earlier

1.41

 decades

1.36

years

1.36

ago

1.28

 YEARS

1.27

 Earlier

1.25

Years

1.25

Activations Density 0.736%

references to digital concepts and their implications in technology

followed by time periods

long ago

No Comments

No Known Activations