INDEX

Explanations

formatting elements within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

tagext

-0.66

UnknownFieldSet

-0.58

 réguli

-0.56

 opérés

-0.55

 surla

-0.55

zugehen

-0.51

 humanas

-0.51

 setAddress

-0.50

бенок

-0.50

 liné

-0.50

POSITIVE LOGITS

 itſelf

0.77

 myſelf

0.59

'{@

0.59

 himſelf

0.55

"]);

0.55

//});

0.53

Diwedd

0.53

]='\

0.53

///</

0.53

Geplaatst

0.53

Activations Density 0.363%

formatting elements within the text

No Comments

No Known Activations