INDEX

Explanations

references to programming or coding terminology

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

The token "Code" and related terms

np_acts-logits-general · gemini-2.0-flash

code 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 @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

GEBURTSDATUM

-0.81

rungsseite

-0.67

 Picchu

-0.66

AsUp

-0.64

mybatisplus

-0.61

 SDLK

-0.60

 NDEBUG

-0.56

runApp

-0.56

}{|

-0.55

appé

-0.55

POSITIVE LOGITS

 getCode

0.81

Co

0.77

Cob

0.74

 Coliseum

0.70

Co

0.65

 covariates

0.64

CoA

0.63

 Colette

0.63

COB

0.62

co

0.61

Activations Density 0.481%

references to programming or coding terminology

The token "Code" and related terms

code and programming terms

No Comments

No Known Activations