INDEX

Explanations

elements related to events and outcomes

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

éphane

-0.61

 Contactez

-0.56

webElementGuid

-0.56

inyl

-0.53

 pageIndex

-0.52

esgue

-0.51

QY

-0.51

 Picchu

-0.50

"</

-0.49

QJ

-0.49

POSITIVE LOGITS

COUVER

0.73

expandindo

0.68

 OFDb

0.65

Демографія

0.62

 насељу

0.61

 autorytatywna

0.61

 Italijanski

0.60

 fieldNum

0.57

 OMITBAD

0.57

+#+#

0.57

Activations Density 0.413%

elements related to events and outcomes

No Comments

No Known Activations