INDEX

Explanations

code-related terms, specifically for main methods and function definitions in programming languages

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

main function entry point

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 برانيه

-0.60

RenderAtEndOf

-0.60

LookAnd

-0.58

adaptiveStyles

-0.55

 cherchés

-0.53

 QtWidgets

-0.51

 endforeach

-0.49

endforeach

-0.48

ErrUnexpectedEOF

-0.48

 виправивши

-0.47

POSITIVE LOGITS

 main

0.95

main

0.82

 Main

0.71

Main

0.71

 MAIN

0.67

__":

0.66

MAIN

0.65

__':

0.57

getMain

0.55

__':

0.52

Activations Density 0.001%

code-related terms, specifically for main methods and function definitions in programming languages

main function entry point

No Comments

No Known Activations