INDEX

Explanations

proper nouns, specifically names and locations related to people and events

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Kearney

-0.80

phorbia

-0.79

 keter

-0.74

 Differenz

-0.74

oporosis

-0.73

𝘤

-0.72

 partielle

-0.72

 Tind

-0.72

mediate

-0.71

IDATE

-0.70

POSITIVE LOGITS

 Magdalen

0.97

 Pais

0.89

 Nagel

0.88

 Île

0.84

 Sjö

0.82

Personensuche

0.82

 Wilma

0.81

 Wilkins

0.81

 Bursa

0.81

 Erdoğan

0.81

Activations Density 2.703%

proper nouns, specifically names and locations related to people and events

No Comments

No Known Activations