INDEX

Explanations

mentions of studios and associated activities

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 Phari

-0.84

glEnd

-0.82

 ?>">

-0.82

))).

-0.78

 Ophelia

-0.75

 Transfermarkt

-0.73

))\

-0.73

Naphthalene

-0.73

 Pring

-0.73

NameInMap

-0.72

POSITIVE LOGITS

 Studio

1.32

 studio

1.31

 studios

1.25

 STUDIO

1.20

Studio

1.19

studio

1.18

STUDIO

1.14

 Studios

1.05

studios

0.98

Studios

0.87

Activations Density 0.122%

mentions of studios and associated activities

No Comments

No Known Activations