INDEX

Explanations

declarations related to programming variables and functions

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

Code or data-related syntax

np_acts-logits-general · gemini-2.0-flash

in critical situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

ReusableCell

-0.73

лтемелер

-0.68

TestingModule

-0.68

 AssemblyCulture

-0.68

 насељу

-0.67

 gynhyrchwyd

-0.64

 للاسماء

-0.64

complexContent

-0.63

Portail

-0.63

hoeddwyd

-0.62

POSITIVE LOGITS

eluarkan

0.47

 Khusus

0.43

 relatie

0.41

 önem

0.41

 particulière

0.40

 specify

0.40

 direta

0.39

 relação

0.38

quela

0.37

 Oliven

0.37

Activations Density 0.840%

declarations related to programming variables and functions

Code or data-related syntax

in critical situations

No Comments

No Known Activations