INDEX

Explanations

patterns related to structured data or identifiers

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

that _ unity

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



-0.60

="@+

-0.59

 surla

-0.57

 NSCoder

-0.53

Tembelea

-0.52

 OFDb

-0.50

 فريبيس

-0.48

 AssemblyVersion

-0.45



-0.45

abstractmethod

-0.45

POSITIVE LOGITS

enterOuterAlt

0.42

TypedDataSet

0.39

saraba

0.37

 autorytatywna

0.36

吹

0.34

 Salter

0.34

 зато

0.34

 regist

0.33

 interven

0.33

Activations Density 0.149%

patterns related to structured data or identifiers

that _ unity

No Comments

No Known Activations