INDEX

Explanations

specific nouns and terms related to various fields, including medicine, physics, and multimedia

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

domain specific phrases

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

 Wohnungen

-0.64

 Öffnungszeiten

-0.59

 Absicht

-0.57

 inmediata

-0.56

 rumahnya

-0.56

 autorité

-0.56

 poszczegól

-0.56

 peraturan

-0.55

 esperança

-0.55

 Verhandlungen

-0.54

POSITIVE LOGITS

 ſte

0.75

 ſta

0.71

 surla

0.70

 tartalomajánló

0.69

 carto

0.68

 Patro

0.66

ChildScrollView

0.66

 multil

0.66

IVEREF

0.65

 digi

0.65

Activations Density 0.413%

specific nouns and terms related to various fields, including medicine, physics, and multimedia

domain specific phrases

No Comments

No Known Activations