INDEX

Explanations

terms related to software components and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

вига

-0.47

="'.$

-0.44

tot

-0.44

 externi

-0.43

 helt

-0.43

hup

-0.42

 عش

-0.42

stdio

-0.41

he

-0.41

,:),

-0.41

POSITIVE LOGITS

XmlAccessType

0.78

 MainAxisSize

0.77

 المعيارى

0.71

::

0.69

 متعلقه

0.69

erçe

0.66

Efq

0.65

 Adnan

0.62

 autorytatywna

0.60

 doubtnut

0.59

Activations Density 0.964%

terms related to software components and programming constructs

No Comments

No Known Activations