INDEX

Explanations

references to various institutes and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 geçti

-0.52

 présentes

-0.48

 Homicide

-0.47

EditForm

-0.46

 Skies

-0.45

 ammi

-0.44

 udara

-0.44

 scrit

-0.43

 Arboretum

-0.42

igr

-0.41

POSITIVE LOGITS

fjspx

1.02

MessageOf

0.82

tagHelperRunner

0.82

 Италијани

0.82

✨:

0.80

].)

0.79

 ModelExpression

0.75

Portale

0.74

amerikanischer

0.74

 Italijanski

0.72

Activations Density 0.059%

references to various institutes and organizations

No Comments

No Known Activations