INDEX

Explanations

mathematical notations or symbols typically used in scientific or technical documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

{}\

-0.67

{}",

-0.64

{\"

-0.63

\"

-0.62

\%,

-0.60

 الرياضيه

-0.58

\%-

-0.57

{},

-0.57

ownerId

-0.55

SOUNDBITE

-0.55

POSITIVE LOGITS

 myſelf

0.69

CppMethod

0.68

<sub>

0.67

 nahilalakip

0.65

 chapels

0.63

 Shakspeare

0.62

 itſelf

0.62

 Cæsar

0.62

 photolibrary

0.61

 Houſe

0.61

Activations Density 0.203%

mathematical notations or symbols typically used in scientific or technical documents

No Comments

No Known Activations