INDEX

Explanations

symbols and characters related to programming code or mathematical notation

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

programming syntax and symbols

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

 betweenstory

-0.50

OCCURRED

-0.48

RectangleBorder

-0.45

writeFieldEnd

-0.39

WebServlet

-0.37

SpringRunner

-0.34

 JpaRepository

-0.31

—

-0.31

Thể

-0.31

 HasFactory

-0.31

POSITIVE LOGITS

 يتيمه

0.59

 թվական

0.47

 execute

0.47

möglichen

0.46

EXEC

0.46

 varandra

0.46

Trayectoria

0.44

dotenv

0.44

 picked

0.44

ⓧ

0.42

Activations Density 0.151%

symbols and characters related to programming code or mathematical notation

programming syntax and symbols

No Comments

No Known Activations