INDEX

Explanations

programming syntax and comments related to code documentation

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

// comments with special characters

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

 Мексичка

-0.65

 erbjud

-0.54

՚

-0.53

WebElementEntity

-0.52

pondre

-0.50

⤹

-0.49

IMPORTED

-0.48

enumi

-0.47

tisgarh

-0.47

itemize

-0.46

POSITIVE LOGITS

//$

0.84

//#

0.78

//[

0.71

//@

0.70

//_

0.64

//<

0.62

///////////////

0.60

//"

0.59

//////

0.59

//{

0.59

Activations Density 0.008%

programming syntax and comments related to code documentation

// comments with special characters

No Comments

No Known Activations