INDEX

Explanations

programming-related terms and features, particularly those associated with defining methods and properties

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

followed by "method" or describing functions

np_acts-logits-general · gemini-2.0-flash

medical deficiency or biological gall

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

TagHelpers

-0.60

ViewChild

-0.60

ucson

-0.54

 bandas

-0.54

 berjudul

-0.53

的眼神

-0.52

ården

-0.51

resizingMask

-0.51

 ویکی‌پدیا

-0.51

 condado

-0.49

POSITIVE LOGITS

 Савезне

0.67

AsUp

0.61

 nakalista

0.61

 Baillargeon

0.60

StreetMap

0.60

saraba

0.60

0.57

PreferredItem

0.57

Diwedd

0.56

#+#

0.55

Activations Density 0.853%

programming-related terms and features, particularly those associated with defining methods and properties

followed by "method" or describing functions

medical deficiency or biological gall

No Comments

No Known Activations