INDEX

Explanations

specific names and proper nouns, particularly related to individuals and places

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Pallas

-0.85

providedIn

-0.83

endphp

-0.82

Huo

-0.80

 dépos

-0.75

 Athena

-0.73

 Brice

-0.71

ettbewer

-0.71

GHS

-0.69

 Mullins

-0.69

POSITIVE LOGITS

rogels

0.76

 Croce

0.74

}');

0.73

 WATSON

0.71

 Lukaku

0.69

 Pfeffer

0.69

 createSprite

0.68

 Kramer

0.68

 Lang

0.67

 Eliot

0.67

Activations Density 2.698%

specific names and proper nouns, particularly related to individuals and places

No Comments

No Known Activations