INDEX

Explanations

elements related to programming classes and functions, particularly those that perform checks or contain specific attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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



-0.61

ViewFeatures

-0.59

EndInit

-0.58

>>()

-0.57

Bav

-0.55

 مشين

-0.55

lieg

-0.55

 cobra

-0.53

TagMode

-0.53

RefNanny

-0.53

POSITIVE LOGITS

TryParse

0.59

 fratelli

0.59

UnitTesting

0.57

 ospiti

0.57

 StringTokenizer

0.57

ุก

0.55

 venait

0.53

 mezzi

0.52

 électroniques

0.52

 navideñas

0.51

Activations Density 0.350%

elements related to programming classes and functions, particularly those that perform checks or contain specific attributes

No Comments

No Known Activations