INDEX

Explanations

numerical values and statistical significance indicators related to research outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 CreateTagHelper

-0.63

RenderAtEndOf

-0.63

WebVitals

-0.62

__':

-0.56

IsMutable

-0.56

 sindaco

-0.56

 виправивши

-0.55

 webbplats

-0.55

 Normdatei

-0.55

tagHelperRunner

-0.55

POSITIVE LOGITS

AnchorStyles

0.59

#+#

0.54

 cref

0.53

 insurance

0.48

urlpatterns

0.47

jekk

0.46

yaar

0.46

aziland

0.45

 slightly

0.44

 bale

0.44

Activations Density 0.598%

numerical values and statistical significance indicators related to research outcomes

No Comments

No Known Activations