INDEX

Explanations

elements and functions related to saving and loading models in Keras

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

racht

-0.50

tinyos

-0.49

 morire

-0.49

})->

-0.48

)((

-0.46

(:,

-0.46

 persoonlijke

-0.43

 immédi

-0.43

<eos>

-0.43

gehende

-0.43

POSITIVE LOGITS

 jsPsych

0.82

ніципалі

0.81

audiovisuel

0.71

:✨

0.71

Hentet

0.70

twimg

0.69

omeness

0.66

 Deum

0.65

 Euph

0.65

 kasarigan

0.65

Activations Density 0.116%

elements and functions related to saving and loading models in Keras

No Comments

No Known Activations