INDEX

Explanations

references to academic institutions and programs

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

transQ

-0.68

OGND

-0.63

 мәкал

-0.61

Obrázky

-0.60

 BrowserModule

-0.60

MessageOf

-0.57

GEBURTSDATUM

-0.56

 invokingState

-0.54

цезда

-0.54

 Terraria

-0.53

POSITIVE LOGITS

MBA

0.46

 GMAT

0.41

 AHEAD

0.40

MBA

0.36

 Ahead

0.33

StrictMode

0.32

writeObject

0.32

templateUrl

0.31

 ahead

0.30

 Wharton

0.29

Activations Density 0.005%

references to academic institutions and programs

No Comments

No Known Activations