INDEX

Explanations

references to an online user or a visitor in a web context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CodeAttribute

-0.50

<?

-0.48

accompagnement

-0.37

HomeAsUpEnabled

-0.35

Formazione

-0.34

MessageTagHelper

-0.34

/**

-0.34

 utafitiHapana

-0.33

aimana

-0.33

 "..\..\

-0.33

POSITIVE LOGITS

:✨

0.66

Personensuche

0.64

NameInMap

0.61

الحياه

0.60

+#+

0.58

出版年

0.55

RTHOOK

0.54

 intptr

0.53

ScopeManager

0.52

 الرياضيه

0.52

Activations Density 0.000%

references to an online user or a visitor in a web context

No Comments

No Known Activations