INDEX

Explanations

references to product identifiers and their attributes

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

judgment entry, contentions, contributing

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 recinto

-0.42

 vlastní

-0.39

 věci

-0.38

Odkazy

-0.38

piers

-0.38

NameInMap

-0.37

 Италијани

-0.36

∮

-0.35

 consci

-0.35

 paralelo

-0.35

POSITIVE LOGITS

PRODUCT

1.50

 PRODUCT

1.07

 productivity

0.79

Productivity

0.78

 Productivity

0.75

produ

0.72

 producti

0.71

productivity

0.70

 Produ

0.69

productive

0.68

Activations Density 0.001%

references to product identifiers and their attributes

judgment entry, contentions, contributing

No Comments

No Known Activations