INDEX

Explanations

programming code structures or patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 resourceCulture

-0.96

enumi

-0.70

abestanden

-0.65

migrationBuilder

-0.64

RetentionPolicy

-0.64

netinet

-0.61

BagLayout

-0.59

Datuak

-0.59

তথ্যসূত্র

-0.58

QMetaType

-0.58

POSITIVE LOGITS

にほんブログ村

0.65

rungsseite

0.57

Климат

0.54

 Spinoza

0.54

 ainfi

0.53

 Drapeau

0.53

 ExecuteAsync

0.52

Výhody

0.52

 fémin

0.51

 graphiques

0.51

Activations Density 0.082%

programming code structures or patterns

No Comments

No Known Activations