INDEX

Explanations

references to specific entities, actions, and interactions in various contexts

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

leadership styles, pathogens, Vibrio, Ag

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 виправивши

-0.53

NameInMap

-0.47

oa̍t

-0.42

featureID

-0.41

 Савезне

-0.41

 BoxFit

-0.40

 ligiloj

-0.39

 Verhältnisse

-0.37

//

-0.36

 onCreateView

-0.36

POSITIVE LOGITS

 fellow

0.51

 competitor

0.50

 rival

0.50

 competitors

0.48

模

0.42

 imit

0.41

fellow

0.41

 rivals

0.40

 cross

0.40

awaiter

0.40

Activations Density 0.443%

references to specific entities, actions, and interactions in various contexts

leadership styles, pathogens, Vibrio, Ag

No Comments

No Known Activations