INDEX

Explanations

overall sentiment and quality assessments of movies and dining experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

 disambiguazione

-0.71

Notae

-0.41

 informée

-0.39

niająca

-0.38

Einzelnachweise

-0.37

 resourceCulture

-0.35

 EconPapers

-0.35

nocześnie

-0.35

 useAppContext

-0.35

laszt

-0.32

POSITIVE LOGITS

 average

1.55

 decent

1.52

 mediocre

1.41

average

1.37

 okay

1.34

 Average

1.32

Average

1.30

ok

1.27

 decently

1.23

 AVERAGE

1.23

Activations Density 0.404%

overall sentiment and quality assessments of movies and dining experiences

No Comments

No Known Activations