INDEX

Explanations

codes, references, or identifiers related to data structures or programming elements

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

ftagPool

-0.81

hyrchwyd

-0.79

 AssemblyVersion

-0.65

bootstrapcdn

-0.65

 estekak

-0.61

JpaRepository

-0.61

 nahilalakip

-0.59

 resourceCulture

-0.57

/**

-0.56

 iNdEx

-0.56

POSITIVE LOGITS

siąż

0.51

Geografía

0.49

 ElementRef

0.49

 Geme

0.47

хьтан

0.46

 Atlas

0.46

Gli

0.46

kuš

0.45

 Exacts

0.45

 JSONException

0.45

Activations Density 0.211%

codes, references, or identifiers related to data structures or programming elements

No Comments

No Known Activations