INDEX

Explanations

data types and variable declarations in programming contexts

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

"int" keyword followed by variable names/identifiers

np_acts-logits-general · gemini-2.0-flash

integer variable declarations

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

 names

-0.93

 itemName

-0.75

 productName

-0.74

 Names

-0.73

Names

-0.70

 newName

-0.68

NameList

-0.68

names

-0.68

 groupName

-0.67

 name

-0.64

POSITIVE LOGITS

TabIndex

0.82

HideFlags

0.81

CloseOperation

0.78

DockStyle

0.73

 CreateTagHelper

0.70

VersionUID

0.70

age

0.69

hashCode

0.68

 number

0.68

исленность

0.66

Activations Density 0.301%

data types and variable declarations in programming contexts

"int" keyword followed by variable names/identifiers

integer variable declarations

No Comments

No Known Activations