INDEX

Explanations

questions and discussions related to organization and documentation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

如果不是

-0.58

omitempty

-0.56

tamol

-0.53

siella

-0.52

ætter

-0.51

ApJ

-0.51

 disponibilités

-0.51

 MNRAS

-0.50

pinMode

-0.49

 Sloveniji

-0.49

POSITIVE LOGITS

 during

0.77

 lors

0.70

during

0.62

 tijdens

0.62

During

0.58

 durante

0.57

lässlich

0.57

Attend

0.57

 attending

0.56

RegistryLite

0.56

Activations Density 0.706%

questions and discussions related to organization and documentation processes

No Comments

No Known Activations