INDEX

Explanations

programming-related terms and code structure

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

Code or hardware register/address manipulation

np_acts-logits-general · gemini-2.0-flash

Bus STOP commands

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 للاسماء

-0.80

 '\\;'

-0.80

 становника

-0.73

 disambiguazione

-0.72

 препратки

-0.71

ArrowToggle

-0.69

 kaarangay

-0.69

ValueStyle

-0.68

BagLayout

-0.67

QMetaType

-0.66

POSITIVE LOGITS

 byte

0.56

byte

0.52

command

0.52

 command

0.49

Byte

0.43

čnih

0.42

COMMAND

0.42

 Command

0.41

 extended

0.41

 Master

0.41

Activations Density 0.433%

programming-related terms and code structure

Code or hardware register/address manipulation

Bus STOP commands

No Comments

No Known Activations