INDEX

Explanations

numerical references and ordinal terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

исленность

-0.78

endphp

-0.68

 disambiguazione

-0.66

tinyos

-0.64

 onCancelled

-0.62

 AttributeSet

-0.60

,:);

-0.60

ⓘ

-0.58

})*/

-0.58

SBATCH

-0.58

POSITIVE LOGITS

 strand

0.55

føring

0.47

ApiModel

0.46

 consideradas

0.43

 piece

0.43

 session

0.42

Serde

0.42

 privadas

0.42

 accesibles

0.41

 complètes

0.41

Activations Density 0.067%

numerical references and ordinal terms

No Comments

No Known Activations