INDEX

Explanations

Japanese sentence-ending particles and phrases indicating actions or states

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

-te conjugations

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 Patro

-0.36

 oignons

-0.36

 setTitle

-0.35

+#+#

-0.35

 newState

-0.35

 reen

-0.33

DataSetChanged

-0.33

 jsonArray

-0.33

"#"

-0.33

\{\\

-0.32

POSITIVE LOGITS

しくて

0.90

があって

0.81

くて

0.80

あって

0.78

していて

0.77

されていて

0.74

っていて

0.73

なくて

0.72

いて

0.68

もあって

0.61

Activations Density 0.006%

Japanese sentence-ending particles and phrases indicating actions or states

-te conjugations

No Comments

No Known Activations