INDEX

Explanations

punctuation and symbols related to choices or options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

rungsseite

-0.71

 الحره

-0.68

 Paglinawan

-0.67

 AssemblyCompany

-0.65

Portail

-0.64

expandindo

-0.63

<bos>

-0.62

脚注の使い方

-0.61

ecuted

-0.59

 CommonModule

-0.59

POSITIVE LOGITS

or

1.25

或

0.92

 или

0.89

หรือ

0.85

or

0.85

 یا

0.81

 atau

0.80

 hoặc

0.80

 또는

0.79

 nebo

0.79

Activations Density 0.211%

punctuation and symbols related to choices or options

No Comments

No Known Activations