INDEX

Explanations

references to online posts and interactions regarding digital content

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

УДК

-0.56

 referenties

-0.56

 ExecuteAsync

-0.52

/*

-0.50

 Pristupljeno

-0.49

 feared

-0.49

aarrggbb

-0.48

โย

-0.48

ooc

-0.47

גי

-0.47

POSITIVE LOGITS

Попис

0.75

WithMany

0.66

 Roskov

0.63

titleMargin

0.63

hoeddwyd

0.58

djangoproject

0.58

 crossorigin

0.58

adaptiveStyles

0.57

PreferredItem

0.56

richTextPanel

0.56

Activations Density 0.066%

references to online posts and interactions regarding digital content

No Comments

No Known Activations