INDEX

Explanations

technical terms and parameters related to data and scientific procedures

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

']->

-0.67

"]];

-0.63

']],

-0.62

AutoScaleMode

-0.60

المكان

-0.59

NameInMap

-0.58

}}-

-0.58

isela

-0.55

 AssemblyCompany

-0.54

érons

-0.54

POSITIVE LOGITS

StoreMessageInfo

0.78

 مشين

0.72

 estekak

0.59

новништво

0.59

IsMutable

0.58

 שוליים

0.57

awtextra

0.57

setVerticalGroup

0.56

ScopeManager

0.56

 Adriatic

0.55

Activations Density 0.025%

technical terms and parameters related to data and scientific procedures

No Comments

No Known Activations