INDEX

Explanations

information related to specific legal and historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Chwiliwch

-0.55

 سكانية

-0.55

Datuak

-0.54

queryInterface

-0.51

hyrchwyd

-0.50

Демографія

-0.49

 Esprit

-0.48

("}");

-0.47

 razie

-0.47

}$.\\

-0.46

POSITIVE LOGITS

IntoConstraints

0.64

먼

0.57

 nahilalakip

0.56

newtheorem

0.55

 sekali

0.55

>{@

0.54

AccessorTable

0.53

 Specifically

0.52

Aiheesta

0.52

prnewswire

0.52

Activations Density 1.207%

information related to specific legal and historical contexts

No Comments

No Known Activations