INDEX

Explanations

proper nouns and specific named entities

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

principalColumn

-0.76

migrationBuilder

-0.71

djangoproject

-0.66

Vidite

-0.66

PhysRev

-0.63

Бахар

-0.63

archiviato

-0.61

PhysRevD

-0.60

Bibliografia

-0.57

Przypisy

-0.57

POSITIVE LOGITS

 originally

0.57

nyttet

0.56

 téléchargez

0.54

intios

0.54

 للاسماء

0.52

 Relaciones

0.51

dox

0.50

 صوتيه

0.49

ترف

0.49

])):

0.48

Activations Density 0.885%

proper nouns and specific named entities

No Comments

No Known Activations