INDEX

Explanations

verbs that denote action or process involving usage and functionality

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

 tenham

-0.69

 esquecer

-0.67

 quæ

-0.65

 tenha

-0.62

 Archangel

-0.62

 brinquedo

-0.60

 attendu

-0.60

 ricevere

-0.59

eachtet

-0.59

 esteja

-0.58

POSITIVE LOGITS

ersburg

0.69

,:]

0.64

]^{-

0.63

'):

0.63

drawSprites

0.63

addContainerGap

0.62

ørs

0.62

'])){

0.61

']?>

0.60

asInstanceOf

0.60

Activations Density 0.149%

verbs that denote action or process involving usage and functionality

No Comments

No Known Activations