INDEX

Explanations

proper nouns, particularly names, places, and organizational affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

oredCriteria

-0.75

lighet

-0.70

WebControls

-0.64

ELTS

-0.63

setupUi

-0.63

Бахар

-0.62

aysia

-0.61

iettivo

-0.58

addCriterion

-0.57

'#'

-0.57

POSITIVE LOGITS

 Marathi

0.78

 Mumbai

0.61

 Kannada

0.60

 Patil

0.58

 Pune

0.58

 Maharashtra

0.58

Pune

0.57

alore

0.57

 CreateTagHelper

0.57

 Bangalore

0.56

Activations Density 0.474%

proper nouns, particularly names, places, and organizational affiliations

No Comments

No Known Activations