INDEX

Explanations

references to webinars, sessions, or educational content focused on development or specific tutorials

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

followed by explanations or discussions

np_acts-logits-general · gemini-2.0-flash

will explain or discuss

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 يتيمه

-0.77

脚注の使い方

-0.63

 initComponents

-0.58

astify

-0.57

FXMLLoader

-0.57

TagMode

-0.53

 isolado

-0.49

ValueStyle

-0.49

SequentialGroup

-0.48

EndContext

-0.48

POSITIVE LOGITS

 discuss

1.38

 covers

1.35

 covered

1.33

 cover

1.30

 discusses

1.28

 covering

1.27

 discussing

1.23

 Covers

1.21

 discussed

1.18

 COVER

1.16

Activations Density 0.377%

references to webinars, sessions, or educational content focused on development or specific tutorials

followed by explanations or discussions

will explain or discuss

No Comments

No Known Activations