INDEX

Explanations

terms related to scientific measurement and evaluation

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

ChildScrollView

-0.52

EndInit

-0.50

enumii

-0.49

AutoScaleMode

-0.47

BeginInit

-0.47

为止

-0.47

ंदीखरीदारी

-0.46

\{\\

-0.46

endphp

-0.44

 transfieras

-0.43

POSITIVE LOGITS

 kaarangay

0.47

eterangan

0.47

 esimer

0.47

 Chats

0.46

Panamoan

0.45

ołnier

0.44

Rosen

0.44

chats

0.43

elton

0.43

InputChange

0.43

Activations Density 0.986%

terms related to scientific measurement and evaluation

No Comments

No Known Activations