INDEX

Explanations

mathematical operators and notation typically used in formal proofs or definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

-0.41

HomeAsUp

-0.39

PÅ

-0.38

Eſ

-0.35

 ellas

-0.34

 rechange

-0.34

 Reſ

-0.34

 cuota

-0.34

 opportunity

-0.33

 sala

-0.33

POSITIVE LOGITS

 تضيفلها

0.72

makeConstraints

0.49

 forState

0.49

 clearColor

0.49

ISupport

0.49

printStackTrace

0.48

BeginInit

0.47

ThroughAttribute

0.47

 protoimpl

0.46

 Infórmanos

0.46

Activations Density 0.390%

mathematical operators and notation typically used in formal proofs or definitions

No Comments

No Known Activations