INDEX

Explanations

terms related to laws, governance, and political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 consultato

-0.79

 odkazy

-0.73

 médicaux

-0.65

 chré

-0.65

 disambiguazione

-0.64

 divertente

-0.64

 estric

-0.64

 <<<<<<<<<<<<<<

-0.61

 choisissez

-0.60

 médicale

-0.60

POSITIVE LOGITS

🏻‍♀️

0.59

Portail

0.55

 virtual

0.55

 civil

0.53

WebElementEntity

0.52

 senior

0.51

."),

0.49

Assured

0.49

 electric

0.49

 oral

0.48

Activations Density 1.159%

terms related to laws, governance, and political contexts

No Comments

No Known Activations