INDEX

Explanations

terms related to historical and cultural influences

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

adjective noun phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

featureID

-0.56

AddTagHelper

-0.54

Straße

-0.49

 Мексичка

-0.49

ELINES

-0.48

Jäh

-0.48

]=-

-0.47

ButtonModule

-0.47

出版年

-0.47

::_('

-0.47

POSITIVE LOGITS

 ujednoznacz

0.60

protoimpl

0.56

 chi̍t

0.54

LabelTagHelper

0.52

SerializedName

0.51

 disambiguazione

0.51

 Seeder

0.51

RuleContext

0.50

 EconPapers

0.50

InjectAttribute

0.49

Activations Density 0.152%

terms related to historical and cultural influences

adjective noun phrases

No Comments

No Known Activations