INDEX

Explanations

connections or references to significant events or concepts related to health, particularly concerning oxygen and disabilities

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

appearing after "and"

np_acts-logits-general · gemini-2.0-flash

connecting technical terms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AddHtmlAttribute

-0.78

 resourceCulture

-0.76

цездатний

-0.73

WebElementEntity

-0.67

rungsseite

-0.66

webElementXpaths

-0.66

 Réponses

-0.65

 AssemblyProduct

-0.64

WriteAttribute

-0.62

sizeCache

-0.62

POSITIVE LOGITS

has

0.79

 allows

0.72

 ultimately

0.72

 ensures

0.68

})();

0.67

 tentunya

0.67

 includes

0.67

 provides

0.67

is

0.65

 enables

0.65

Activations Density 0.456%

connections or references to significant events or concepts related to health, particularly concerning oxygen and disabilities

appearing after "and"

connecting technical terms

No Comments

No Known Activations