INDEX

Explanations

references to personal attributes and characteristics related to intelligence and social behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

tvguidetime

-0.88

SpringBootTest

-0.78

 otomatig

-0.73

yntaxException

-0.72

tableFuture

-0.71

logous

-0.69

ResponseWriter

-0.68

GenerationType

-0.68

consulté

-0.68

GEBURTSDATUM

-0.67

POSITIVE LOGITS

 meticulous

0.77

 picky

0.75

 perfection

0.72

 fasti

0.68

 obsessive

0.68

 stubborn

0.67

 prolific

0.67

 compulsive

0.66

 fussy

0.64

 nature

0.63

Activations Density 0.272%

references to personal attributes and characteristics related to intelligence and social behaviors

No Comments

No Known Activations