INDEX

Explanations

terms related to programming and software development tools

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

python model form definitions

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

principalTable

-0.49

principalColumn

-0.43

PINES

-0.38

 Examiners

-0.38

moveToFirst

-0.36

interopRequire

-0.36

 Lokales

-0.36

édie

-0.36

 hứng

-0.35

codehaus

-0.35

POSITIVE LOGITS

Бахар

1.34

PERMISSION

1.27

protoimpl

1.03

basicConfig

0.89

ModelSerializer

0.88

XmlAccessorType

0.79

 resourceCulture

0.78

ModelForm

0.76

TimerTask

0.71

 UnityEditor

0.69

Activations Density 0.000%

terms related to programming and software development tools

python model form definitions

No Comments

No Known Activations