INDEX

Explanations

statistics related to input/output operations and system performance

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

attribute value assignments

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

parsedMessage

-0.71

AnchorStyles

-0.67

LookAnd

-0.58

StoryboardSegue

-0.57

 pageContext

-0.57

AutoScaleMode

-0.55

Obrázky

-0.54

tagHelperRunner

-0.52

 Walkover

-0.51

SPJ

-0.49

POSITIVE LOGITS

 estimates

0.54

 estimated

0.52

 total

0.52

 amount

0.50

 estimation

0.49

 amounts

0.48

 estimate

0.46

 totals

0.46

 jumlah

0.46

 estimations

0.46

Activations Density 0.048%

statistics related to input/output operations and system performance

attribute value assignments

No Comments

No Known Activations