INDEX

Explanations

references to specific methods and calls related to APIs and data handling

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

URLs and file paths

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 المعيارى

-0.96

 يتيمه

-0.79

 BoxFit

-0.73

oredCriteria

-0.66

دانشنامهٔ

-0.65

aarrggbb

-0.63

principalColumn

-0.62

elemField

-0.62

 Administrativna

-0.61

 فريبيس

-0.57

POSITIVE LOGITS

 tiet

0.47

 tärke

0.40

 avulla

0.38

Ufficio

0.36

 vastaan

0.34

 lopp

0.34

 valmis

0.34

Cyfeiriadau

0.33

XmlRootElement

0.33

كويكب

0.33

Activations Density 0.001%

references to specific methods and calls related to APIs and data handling

URLs and file paths

No Comments

No Known Activations