INDEX

Explanations

references to media-related topics and concepts

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

"media"

np_acts-logits-general · gemini-2.0-flash

media literacy and rights

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

CloseOperation

-0.53

providedIn

-0.42

ViewChild

-0.39

Ell

-0.38

UseVisualStyle

-0.37

Zav

-0.36

Ell

-0.35

abstractmethod

-0.35

stdlib

-0.35

󠁧

-0.34

POSITIVE LOGITS

bootstrapcdn

0.69

 Media

0.64

Media

0.63

 MEDIA

0.55

 Medien

0.54

 media

0.50

MEDIA

0.49

 scrum

0.47

 outlets

0.46

媒

0.46

Activations Density 0.138%

references to media-related topics and concepts

"media"

media literacy and rights

No Comments

No Known Activations