INDEX

Explanations

expressions relating to distraction and attention diversion

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

Personendaten

-0.72

 dentelle

-0.62

 danni

-0.60

esez

-0.60

 poussière

-0.59

empereur

-0.57

 dégâts

-0.56

 Arce

-0.56

Hauptartikel

-0.56

 rischi

-0.55

POSITIVE LOGITS

 distract

0.77

 distraction

0.68

 distra

0.67

 distractions

0.66

 distracting

0.66

 offset

0.66

 Distra

0.63

$__

0.59

 offsets

0.58

 diversion

0.57

Activations Density 0.319%

expressions relating to distraction and attention diversion

No Comments

No Known Activations