INDEX

Explanations

names of individuals and references related to genetics or programming structures

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

Characters or symbols not in the alphabet

np_acts-logits-general · gemini-2.0-flash

special characters and abbreviations

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

 للاسماء

-0.71

 AssemblyTitle

-0.67

ագրություններ

-0.66

 Roskov

-0.64

 <=",

-0.63

 <<<<<<<<<<<<<<

-0.62

HasAnnotation

-0.61

EndContext

-0.61

 lenker

-0.60

 useAppContext

-0.60

POSITIVE LOGITS

LookAnd

0.42

 pourront

0.40

 potranno

0.37

 ocupación

0.37

 acela

0.36

 vrais

0.35

 olmayan

0.35

 boneka

0.34

 potrebbero

0.34

 Aérea

0.34

Activations Density 1.332%

names of individuals and references related to genetics or programming structures

Characters or symbols not in the alphabet

special characters and abbreviations

No Comments

No Known Activations