INDEX

Explanations

occurrences of the preposition "in" along with its context in phrases indicating conditions, states, or agreement

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

"in"

np_acts-logits-general · gemini-2.0-flash

in agreement

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ugges

-0.50

parsedMessage

-0.49

 LEYENDO

-0.47

rawDesc

-0.45

بوابة

-0.44

withOpacity

-0.43

randomUUID

-0.43

 recomendamos

-0.43

BibitemShut

-0.43

devamını

-0.42

POSITIVE LOGITS

новниш

0.45

.*")]

0.43

 находится

0.38

 ordres

0.38

🍚

0.37

nestjs

0.36

rizona

0.36

}{||

0.36

 proportional

0.35

 Putnam

0.35

Activations Density 0.341%

occurrences of the preposition "in" along with its context in phrases indicating conditions, states, or agreement

"in"

in agreement

No Comments

No Known Activations