INDEX

Explanations

identifiers related to regions or locations

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

hex digits

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

出版年

-0.93

 հղումներ

-0.67

 BrowserModule

-0.63

 HasFactory

-0.58

XmlAccessType

-0.58

VersionUID

-0.57

<?

-0.55

providedIn

-0.54

MigrationBuilder

-0.54

SharedDtor

-0.52

POSITIVE LOGITS

 mukana

0.40

0.39

ésult

0.37

zten

0.34

Th

0.33

íslu

0.32

 thermique

0.32

 tabung

0.32



0.31

Activations Density 0.073%

identifiers related to regions or locations

hex digits

No Comments

No Known Activations

identifiers related to regions or locations

hex digits

No Comments

No Known Activations