INDEX

Explanations

instances of lists or enumerations in the text

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

"List" followed by what to list

np_acts-logits-general · gemini-2.0-flash

list the

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MemoryWarning

-0.77

imageshack

-0.73

MigrationBuilder

-0.71

batore

-0.71

hoots

-0.69

הערות

-0.68

Искәрмәләр

-0.66

сылкі

-0.64

 khảo

-0.64

VersionUID

-0.63

POSITIVE LOGITS

 newList

0.95

 Lists

0.85

mybatisplus

0.77

 lists

0.75

 LIST

0.73

 list

0.67

 itemList

0.66

 mList

0.65

lists

0.65

Lists

0.63

Activations Density 0.151%

instances of lists or enumerations in the text

"List" followed by what to list

list the

No Comments

No Known Activations