INDEX

Explanations

terms related to programming constructs and methodologies

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

technical documentation and code snippets

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

CppMethod

-0.60

QMetaType

-0.54

GOTREF

-0.44

complexContent

-0.44

onAttach

-0.43

LookAnd

-0.42

 виправивши

-0.40

principalColumn

-0.40

addWidget

-0.39

rawDesc

-0.39

POSITIVE LOGITS

новништво

0.57

出版年

0.46

市镇

0.45

WindowConstants

0.45

 StatelessWidget

0.42

ⓧ

0.41

:✨

0.40

assin

0.40

stini

0.39

Sucesor

0.39

Activations Density 0.023%

terms related to programming constructs and methodologies

technical documentation and code snippets

No Comments

No Known Activations