INDEX

Explanations

information about personal experiences and professions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

addCriterion

-0.67

 transférez

-0.58

enumi

-0.53

QMetaType

-0.53

 <>",

-0.53

 <<<<<<<<<<<<<<

-0.51

ficado

-0.48

 GetEnumerator

-0.48

おめでとうございます

-0.48

 iprot

-0.47

POSITIVE LOGITS

ViewImports

0.66

 myſelf

0.62

BeginInit

0.59

TabIndex

0.57

 myself

0.56

DockStyle

0.53

endphp

0.51

reht

0.51

ABN

0.50

Ond

0.49

Activations Density 0.413%

information about personal experiences and professions

No Comments

No Known Activations