INDEX

Explanations

symbols and formatting used in mathematical or scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

CloseOperation

-0.65

ReusableCell

-0.59

 initComponents

-0.52

MigrationBuilder

-0.50

photobucket

-0.49

AnimationsModule

-0.48

tvguidetime

-0.48

principalColumn

-0.47

#+#

-0.47

曖昧さ回避

-0.47

POSITIVE LOGITS

textbf

0.49

 manteau

0.42

bold

0.41

mathbf

0.40

<b>

0.40

-------

0.39

)**

0.38

 manto

0.38

Tito

0.37

 devo

0.37

Activations Density 0.397%

symbols and formatting used in mathematical or scientific contexts

No Comments

No Known Activations