INDEX

Explanations

sections of text that contain metadata or descriptors related to content organization and context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

aarrggbb

-0.83

mybatisplus

-0.78

 propOrder

-0.77

 متعلقه

-0.72

 utafitiHapana

-0.71

 تضيفلها

-0.69

insee

-0.68

igshid

-0.68

liferay

-0.68

⟭

-0.66

POSITIVE LOGITS

原始内容存档于

0.61

 soprav

0.56

 popoli

0.54

=*/

0.53

 mắn

0.53

 patrio

0.53

"]="

0.53

 soldati

0.52

 potuto

0.52

 dừng

0.50

Activations Density 0.073%

sections of text that contain metadata or descriptors related to content organization and context

No Comments

No Known Activations