INDEX

Explanations

references and citations to sections and algorithms within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

MAR

-0.57

mar

-0.57

hach

-0.55

Mar

-0.54

 Blue

-0.50

 Golden

-0.47

↵↵

-0.47

 nark

-0.47

Mar

-0.46

 multiple

-0.46

POSITIVE LOGITS

الإنجليزية

0.88

 hereof

0.82

 &___

0.82

 <<<<<<<<<<<<<<

0.81

تفصیلات

0.79

 للمعارف

0.79

✨:

0.78

Efq

0.75

 propOrder

0.75

 ainfi

0.74

Activations Density 1.114%

references and citations to sections and algorithms within a document

No Comments

No Known Activations