INDEX

Explanations

phrases related to predicting outcomes in data processing or machine learning contexts

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

predicts outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 solidaridad

-0.38

EndContext

-0.30

 versiones

-0.29

 orologio

-0.29

íí

-0.29

 diciendo

-0.29

 joyas

-0.28

 ahorro

-0.28

 telling

-0.28

 miembros

-0.28

POSITIVE LOGITS

bootstrapcdn

0.71

WebElementEntity

0.65

MLLoader

0.63

GEBURTSDATUM

0.62

 '\\;'

0.60

OGND

0.59

 فريبيس

0.58



0.57

TypedDataSet

0.57

 intptr

0.57

Activations Density 0.058%

phrases related to predicting outcomes in data processing or machine learning contexts

predicts outcomes

No Comments

No Known Activations