INDEX

Explanations

terms related to positive and negative values in mathematical or statistical analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 referenties

-0.62

 Athene

-0.58

 himſelf

-0.56

DockStyle

-0.54

ATEN

-0.54

 defaults

-0.52

 elbow

-0.51

Cæ

-0.50

 Kase

-0.50

 Arag

-0.50

POSITIVE LOGITS

ConstraintMaker

0.67

 Réponses

0.63

enumii

0.58

saraba

0.58

 незавершена

0.57

ViewFeatures

0.56

BufferException

0.54

 MainAxisSize

0.54

 positive

0.53

JspWriter

0.53

Activations Density 0.975%

terms related to positive and negative values in mathematical or statistical analysis

No Comments

No Known Activations