INDEX

Explanations

significant transformations and relationships between characters

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

joining or partnering with others

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

-------------</

-0.47

 Exacts

-0.44

 EconPapers

-0.40

ViewImports

-0.39

 whereof

-0.39

KommentareTeilen

-0.38

RuleContext

-0.38

stdc

-0.38

featureID

-0.37

 invokingState

-0.37

POSITIVE LOGITS

 Ketten

0.41

HasAnnotation

0.41

 vermelhas

0.41

 rospy

0.40

ulement

0.38

occasione

0.37

 vagas

0.37

SPO

0.37

UnifiedTopology

0.37

zeugen

0.37

Activations Density 0.059%

significant transformations and relationships between characters

joining or partnering with others

No Comments

No Known Activations