INDEX

Explanations

occurrences of the word "one" and its variants in different contexts, emphasizing singularity or focus on specific items or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

expandindo

-1.10

Autoritní

-0.80

 Cæsar

-0.75



-0.74

Tikang

-0.71

Diweddarwch

-0.70

Xna

-0.68

Bibliograf

-0.68

TemporalType

-0.68

Переваги

-0.67

POSITIVE LOGITS

One

0.74

One

0.69

>::

0.66

мум

0.66

}],

0.62

)}</

0.61

two

0.57

}}],

0.57

"}},

0.57

 reason

0.56

Activations Density 0.202%

occurrences of the word "one" and its variants in different contexts, emphasizing singularity or focus on specific items or concepts

No Comments

No Known Activations