INDEX

Explanations

references to companies and products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 Réponses

-0.65

ativement

-0.57

});*/

-0.55

MessageOf

-0.55

:✨

-0.55

 extra

-0.53

 resourceCulture

-0.53

cic

-0.53

readObject

-0.52

 שוליים

-0.51

POSITIVE LOGITS

 houſe

0.78

 Houſe

0.70

 étoient

0.68

 pouvoit

0.62

 gratuites

0.62

 mourut

0.61

 étoit

0.60

 heureuse

0.60

 Spherical

0.60

 melanin

0.59

Activations Density 0.864%

references to companies and products

No Comments

No Known Activations