INDEX

Explanations

technical code structures and comments in programming content

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

Code or placeholder comments

np_acts-logits-general · gemini-2.0-flash

code comments and programming terms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 سكانية

-0.68

seamnă

-0.66

 itſelf

-0.65

AsUp

-0.63

SharedCtor

-0.62

帖最后由

-0.61

 betweenstory

-0.60

verständlich

-0.60

 poffible

-0.59

 oprot

-0.59

POSITIVE LOGITS

AutoresizingMask

0.68

XMLSchema

0.67

 StyleSheet

0.65

XtraReports

0.62

alama

0.58

 wikipagina

0.56

styleUrls

0.56

iserie

0.56

StyleSheet

0.55

providedIn

0.54

Activations Density 0.325%

technical code structures and comments in programming content

Code or placeholder comments

code comments and programming terms

No Comments

No Known Activations