INDEX

Explanations

specific numerical values and document-related terms

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

patent numbers and citations

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

SharedDtor

-0.60

 صوتيه

-0.59

matchCondition

-0.57

 الحره

-0.56

ConstraintMaker

-0.56

 فريبيس

-0.53

awaiter

-0.52

richTextPanel

-0.51

 propOrder

-0.50

 pinulongan

-0.50

POSITIVE LOGITS

Fum

0.39

fum

0.35

Fo

0.34

Пере

0.33

зован

0.33

 vụ

0.33

NC

0.32

 Пере

0.32

 defStyle

0.32

 rena

0.31

Activations Density 0.176%

specific numerical values and document-related terms

patent numbers and citations

No Comments

No Known Activations

specific numerical values and document-related terms

patent numbers and citations

No Comments

No Known Activations