INDEX

Explanations

references to online resources and archived content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

 initComponents

-0.47

paramref

-0.46

tinyos

-0.43

Становништво

-0.42

 propOrder

-0.41

商品説明

-0.41

DockStyle

-0.40

ингл

-0.39

:✨

-0.39

optional

-0.37

POSITIVE LOGITS

 оригіналу

0.81

 محفوظة

0.73

原始内容存档于

0.71

 Wayback

0.69

 arşivlendi

0.66

 Archive

0.65

 archive

0.64

archive

0.59

 archived

0.58

Archive

0.57

Activations Density 0.069%

references to online resources and archived content

No Comments

No Known Activations