INDEX

Explanations

keywords and logic related to object-oriented programming concepts, particularly instance checking and method overrides

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ⓧ

-0.70

 protoimpl

-0.68

aarrggbb

-0.67

ukone

-0.66

HtmlAttribute

-0.65

makeConstraints

-0.64

ViewFeatures

-0.63

 InputDecoration

-0.62

 RISERVATA

-0.60

WindowConstants

-0.60

POSITIVE LOGITS

 instanceof

1.06

 isinstance

1.04

getClass

0.95

 typeof

0.94

typeof

0.90

 isKindOfClass

0.89

isinstance

0.87

GetType

0.83

InstanceOf

0.79

 type

0.77

Activations Density 0.276%

keywords and logic related to object-oriented programming concepts, particularly instance checking and method overrides

No Comments

No Known Activations