INDEX

Explanations

import statements from Java and Android libraries

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

apache commons math tests

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

 protoimpl

-0.52

oredCriteria

-0.50

WaitGroup

-0.50

 mergeFrom

-0.49

Personendaten

-0.48

 invokingState

-0.47

 Chwiliwch

-0.47

GTCX

-0.45

 Normdatei

-0.45

ScopeManager

-0.44

POSITIVE LOGITS

 cref

0.39

 näm

0.37

BindingSource

0.36

 logiciels

0.34

Own

0.32

tagHelper

0.32

})();

0.32

ymce

0.32

 Membuat

0.31

 Mumbai

0.31

Activations Density 0.008%

import statements from Java and Android libraries

apache commons math tests

No Comments

No Known Activations