INDEX

Explanations

numerical data, specifically dates and counts

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

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

'}';

-0.60

 numerus

-0.56

=$?

-0.53

pezi

-0.52

riwal

-0.48

EndInit

-0.48

programma

-0.48

featureID

-0.47

 makeStyles

-0.47

scrollTop

-0.47

POSITIVE LOGITS

 afternoon

0.74

 morning

0.69

 архивлан

0.65

 uſed

0.60

 ویکی‌پدی

0.60

kuuta

0.60

Portale

0.58

 purpoſe

0.57

SourceChecksum

0.57

DllImport

0.57

Activations Density 0.378%

numerical data, specifically dates and counts

No Comments

No Known Activations