INDEX

Explanations

references to different modes or states within a system

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

?>

-0.75

 fluorine

-0.69

']->

-0.68

************

-0.67

fetch

-0.66

))\

-0.64

Bioaccumulative

-0.64

 methyl

-0.63

xss

-0.62

ggg

-0.62

POSITIVE LOGITS

 Mode

1.67

 Modes

1.60

modes

1.58

 modes

1.58

 MODE

1.55

Modes

1.50

 mode

1.50

mode

1.47

Mode

1.44

setMode

1.37

Activations Density 0.113%

references to different modes or states within a system

No Comments

No Known Activations