INDEX

Explanations

programming terms and structure often used in data structures and algorithms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 AssemblyCulture

-0.60

 متعلقه

-0.57

 Subs

-0.53

álva

-0.51

kloped

-0.51

 Мексичка

-0.50

::::::::

-0.50

bootstrapcdn

-0.49

itudinal

-0.49

hafte

-0.48

POSITIVE LOGITS

/>";

0.63

OrBuilder

0.63

moveToFirst

0.58

 viewDidLoad

0.56

Efq

0.55

RegistryLite

0.54

 ListNode

0.54

 culturali

0.53

CppMethod

0.50

IsMutable

0.50

Activations Density 0.620%

programming terms and structure often used in data structures and algorithms

No Comments

No Known Activations