INDEX

Explanations

specific terminology and components related to medical devices and assembly

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

automatic processes and devices

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

principalColumn

-0.50

contentLoaded

-0.49

sizeCache

-0.48

 Roskov

-0.47

WEBPACK

-0.47

日閲覧

-0.46

っか

-0.44

tagHelperRunner

-0.43

 StatefulWidget

-0.43

 CreateTagHelper

-0.43

POSITIVE LOGITS

 automatically

0.66

 automáticamente

0.63

 automatiquement

0.60

automatically

0.56

Automatically

0.54

 automatiques

0.53

 otomatis

0.53

 antemano

0.51

 Automatically

0.50

 automatique

0.50

Activations Density 0.222%

specific terminology and components related to medical devices and assembly

automatic processes and devices

No Comments

No Known Activations