INDEX

Explanations

occurrences of programming-related keywords, particularly those associated with namespaces and using directives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 فريبيس

-0.56

 verra

-0.49

SLP

-0.45

 MatDialog

-0.44

 signs

-0.43

 andes

-0.43

 cerimonia

-0.43

jstor

-0.42

chica

-0.41

 censiti

-0.41

POSITIVE LOGITS

namespace

1.63

帖最后由

1.01

Portail

0.97

 AssemblyTitle

0.87

RegressionTest

0.85

 <<<<<<<<<<<<<<

0.83

Datuak

0.81

package

0.79

بوابة

0.78

fjspx

0.75

Activations Density 0.016%

occurrences of programming-related keywords, particularly those associated with namespaces and using directives

No Comments

No Known Activations