INDEX

Explanations

instances of the term "include" indicating header file inclusions in code

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

code include statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ngrx

-0.65

 unknownFields

-0.61

IsMutable

-0.60

AsUp

-0.59

formik

-0.59

 DataTypes

-0.59

ymm

-0.56

neurial

-0.54

abetes

-0.54

cuit

-0.54

POSITIVE LOGITS

include

0.76

printStackTrace

0.47

usepackage

0.45

__(/*!

0.44

Include

0.42

++]

0.41

INCLUDE

0.40

ViewFeatures

0.40

 nahilalakip

0.40

freopen

0.36

Activations Density 0.008%

instances of the term "include" indicating header file inclusions in code

code include statements

No Comments

No Known Activations