INDEX

Explanations

references to feature selection and data processing

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

 radiating

-0.67

Искәрмәләр

-0.66

 propagating

-0.63

 crucified

-0.60

 reaſon

-0.60

 poffible

-0.59

 slaughtered

-0.59

 soñ

-0.59

 plastered

-0.58

rilled

-0.57

POSITIVE LOGITS

 stringBy

0.54

りゃ

0.54

newtheorem

0.54

 Italijani

0.53

 CascadeType

0.53

STOT

0.53

TableAdapter

0.52

 climatisation

0.51

esticular

0.51

 event

0.49

Activations Density 1.195%

references to feature selection and data processing

No Comments

No Known Activations