INDEX

Explanations

occurrences of specific programming and API keywords

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

登場

-0.79

少ない

-0.71

増

-0.71

いる

-0.70

มี

-0.67

出演

-0.66

จะ

-0.64

悪

-0.63

ある

-0.62

出て

-0.62

POSITIVE LOGITS

 pinulongan

0.50

$_['

0.46

 SDLK

0.42

Hauptartikel

0.42

了嗎

0.40

Eigenschaften

0.39

ggiamento

0.39

erialization

0.39

izacja

0.38

MLLoader

0.38

Activations Density 0.061%

occurrences of specific programming and API keywords

No Comments

No Known Activations