INDEX

Explanations

programming-related keywords and terms within technical documentation

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

Spoljašnje

-0.57

<?

-0.55

Specifier

-0.55

 mourir

-0.54

assurer

-0.52

 Médico

-0.51

rekli

-0.50

 nooit

-0.49

 corneal

-0.49

umenical

-0.49

POSITIVE LOGITS

ExecutionContext

4.08

はじめに

0.91

 Execution

0.85

 متعلقه

0.83

 الرياضيه

0.76

 estekak

0.76

tagHelper

0.76

 execution

0.72

ViewFeatures

0.69

مراجع

0.67

Activations Density 0.009%

programming-related keywords and terms within technical documentation

No Comments

No Known Activations