INDEX

Explanations

patterns of author names and affiliations in scientific citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

^(@)

-0.89

verwijspagina

-0.87

 ſche

-0.86

зулта

-0.85

 وتسجيلات

-0.85

NameInMap

-0.83

})*/

-0.81

 houſe

-0.81

 Majefty

-0.80

 myſelf

-0.80

POSITIVE LOGITS

eds

1.05

0.78

 respectivamente

0.67

 respectively

0.65

0.64

Eds

0.62

 Their

0.61

 alike

0.58

Their

0.56

Activations Density 0.302%

patterns of author names and affiliations in scientific citations

No Comments

No Known Activations