INDEX

Explanations

technical terms and identifiers related to software frameworks and programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 utafitiHapana

-0.62

?}",

-0.57

 Administrativna

-0.57

 المعيارى

-0.54

 Arki

-0.51

&[

-0.50

 krav

-0.49

!("{}",

-0.49

couvrez

-0.48

MethodManager

-0.48

POSITIVE LOGITS

 оригіналу

0.79

GEBURTSDATUM

0.76

FontOfSize

0.69

BeginContext

0.65

TagMode

0.63

 XNUMX

0.62

 estimés

0.60

addGap

0.60

יבה

0.60

 محفوظة

0.59

Activations Density 1.682%

technical terms and identifiers related to software frameworks and programming languages

No Comments

No Known Activations