INDEX

Explanations

programming-related elements, particularly those related to namespaces and use statements in code

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

Code imports or namespaces

np_acts-logits-general · gemini-2.0-flash

programming libraries and namespaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

brigens

-0.33

 descenso

-0.32

gsmål

-0.30

 ascenso

-0.30

 íntimo

-0.30

 lèvres

-0.29

 čierna

-0.28

 poitrine

-0.28

 quedado

-0.27

 AppCompatTheme

-0.26

POSITIVE LOGITS

 '\\;'

0.71

Notae

0.68

StoryboardSegue

0.64

 Illuminate

0.60

 pinulongan

0.59

\{\\

0.57

App

0.57

Portály

0.56

Har

0.55

 ligiloj

0.54

Activations Density 0.010%

programming-related elements, particularly those related to namespaces and use statements in code

Code imports or namespaces

programming libraries and namespaces

No Comments

No Known Activations