INDEX

Explanations

references to structures, particularly those prefixed with "bar" or related to visual representations

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

 متعلقه

-1.21

)");

-0.89

__':

-0.89

.)}

-0.89

--}}

-0.88

>")

-0.87

$")

-0.86

');?>

-0.86

 betweenstory

-0.86

")){

-0.85

POSITIVE LOGITS

bar

1.49

BAR

1.46

bar

1.45

BAR

1.42

Bar

1.42

Bar

1.40

 bars

1.40

Bars

1.28

 Bars

1.26

bars

1.20

Activations Density 0.087%

references to structures, particularly those prefixed with "bar" or related to visual representations

No Comments

No Known Activations