INDEX

Explanations

interrogative phrases and question words related to seeking information

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

Question words (what, when, how, why)

np_acts-logits-general · gemini-2.0-flash

question words like how and why

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 समीक्षाओं

-0.42

AccessorTable

-0.42

Спољашње

-0.40

AddTagHelper

-0.38

Hochspringen

-0.36

 snippetHide

-0.36

 Ause

-0.35

 صوتيه

-0.35

adaptiveStyles

-0.35

وصلات

-0.34

POSITIVE LOGITS

WithMany

0.50

 onBackPressed

0.49

Jeografia

0.48

qrstuvwxyz

0.47

Parcelize

0.47

 StatefulWidget

0.46

how

0.46

 WHAT

0.45

HOW

0.45

NewUrlParser

0.45

Activations Density 0.387%

interrogative phrases and question words related to seeking information

Question words (what, when, how, why)

question words like how and why

No Comments

No Known Activations