INDEX

Explanations

data related to numerical values and statistics, particularly in a comparative context

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

numbers followed by figures or tables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

tagHelperRunner

-0.67

OGND

-0.56

WebElementEntity

-0.54

 ostavi

-0.52

 Мексичка

-0.50

awtextra

-0.50

TagMode

-0.49

RuleContext

-0.49

/*---

-0.49

зулта

-0.48

POSITIVE LOGITS

tangentMode

0.47

 muchacha

0.39

ViewFeatures

0.37

 Herkunft

0.36

Exercise

0.36

 Gabri

0.36

 temprano

0.36

ริง

0.36

 مارس

0.35

 temprana

0.35

Activations Density 0.007%

data related to numerical values and statistics, particularly in a comparative context

numbers followed by figures or tables

No Comments

No Known Activations