INDEX

Explanations

key terms and identifiers related to programming structures, particularly in code related to data handling and challenging mathematical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

hasMoreElements

-0.81

InjectAttribute

-0.75

QMetaType

-0.72

NameInMap

-0.69

parseColor

-0.68

EndContext

-0.67

IconModule

-0.67

ViewImports

-0.67

ValueStyle

-0.65

stateMutability

-0.64

POSITIVE LOGITS

 Fray

0.59

Fixtures

0.57

HAY

0.57

 Amos

0.57

einander

0.57

Fay

0.57

vrt

0.57

 bowels

0.57

 levy

0.56

 stencils

0.56

Activations Density 0.019%

key terms and identifiers related to programming structures, particularly in code related to data handling and challenging mathematical concepts

No Comments

No Known Activations