INDEX

Explanations

code snippets and programming-related terms

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

Code, XML, or programming-related text

np_acts-logits-general · gemini-2.0-flash

user turn identifier

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

queryInterface

-0.39

GRANTED

-0.37

contentPane

-0.35

Positioned

-0.35

">//

-0.35

 nghỉ

-0.34

orElseThrow

-0.34

XDECREF

-0.33

anlage

-0.32

 angelegt

-0.32

POSITIVE LOGITS

apatalk

0.57

 EconPapers

0.55

featureID

0.55

transQ

0.53

 CanadaChoose

0.52

 Италијани

0.50

تقاوى

0.50

Datuak

0.49

findpost

0.48

+#+#

0.48

Activations Density 0.243%

code snippets and programming-related terms

Code, XML, or programming-related text

user turn identifier

No Comments

No Known Activations