INDEX

Explanations

function definitions and calls in programming code

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

ViewFeatures, defaultProps, setArguments

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

 propOrder

-0.64

FunctionFlags

-0.63

usercontent

-0.57

 jspb

-0.56

parsedMessage

-0.54

basicConfig

-0.52

oredCriteria

-0.51

bcryptjs

-0.49

inSlope

-0.49

 OFDb

-0.49

POSITIVE LOGITS

ViewFeatures

0.40

Putting

0.35

 Putting

0.34

centralwidget

0.33

 rolle

0.32

 putting

0.30

defaultProps

0.30

setArguments

0.30

 Estaba

0.29

 stelt

0.29

Activations Density 0.005%

function definitions and calls in programming code

ViewFeatures, defaultProps, setArguments

No Comments

No Known Activations