INDEX

Explanations

phrases related to rates, especially those introduced with "per."

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

"per [unit of measure/time]"

np_acts-logits-general · gemini-2.0-flash

rates per unit

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ViewFeatures

-0.51

’

-0.48

RUCT

-0.47

 remettre

-0.44

toHaveBeen

-0.43

 lief

-0.43

 initComponents

-0.42

 CoreData

-0.42

getItemId

-0.41

POSITIVE LOGITS

 annum

0.95

 متعلقه

0.88

IUrlHelper

0.87

verwijspagina

0.82

 JpaRepository

0.81

FontOfSize

0.79

uxxxx

0.79

(&:

0.76

Chaque

0.76

UIControlState

0.76

Activations Density 0.117%

phrases related to rates, especially those introduced with "per."

"per [unit of measure/time]"

rates per unit

No Comments

No Known Activations