INDEX

Explanations

structured data representations and references to studies

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

]<<

-0.69

]--;

-0.64

}}_{\

-0.61

++]=

-0.61

)=>{

-0.58

achim

-0.56

ervis

-0.55

TagHelper

-0.54

ocha

-0.54

]='\

-0.53

POSITIVE LOGITS

StoryboardSegue

0.84

Cyfeiriadau

0.75

Obrázky

0.69

MessageTagHelper

0.67

 defStyle

0.65

featureID

0.64

routeProvider

0.61

 umane

0.60

ValueStyle

0.60

formik

0.59

Activations Density 0.391%

structured data representations and references to studies

No Comments

No Known Activations