INDEX

Explanations

references to scientific disciplines and related terminology

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nodoc

-0.69

Hochspringen

-0.63

ที่ยว

-0.59

 Arian

-0.58

IVEREF

-0.57

hubaneswar

-0.57

 مشين

-0.56

ikistan

-0.55

Bronnen

-0.54

 anatomy

-0.54

POSITIVE LOGITS

ItemBackground

0.59

 Familienname

0.59

grafico

0.56

casila

0.56

InSection

0.56

 Beres

0.55

ArrowToggle

0.55

 presidencial

0.54

PhysRevD

0.54

PMailer

0.52

Activations Density 0.032%

references to scientific disciplines and related terminology

No Comments

No Known Activations