INDEX

Explanations

terms related to software testing and utilities

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

test files

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

 AssemblyVersion

-0.51

 ujednoznacz

-0.43

GraphicsUnit

-0.43

CloseOperation

-0.42

 الحره

-0.41

出版年

-0.41

 autorytatywna

-0.40

хьтан

-0.40

BindingResult

-0.38

 désolés

-0.38

POSITIVE LOGITS

Diweddarwch

0.51

 Test

0.49

 TestBed

0.49

TestUtils

0.46

 test

0.45

 Testing

0.45

 Tests

0.44

ftest

0.43

TestingModule

0.43

vician

0.43

Activations Density 0.013%

terms related to software testing and utilities

test files

No Comments

No Known Activations