INDEX

Explanations

key terms related to research methodology and results in scientific literature

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

determination and identification

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

 tartalomajánló

-0.95

elemField

-0.90

parsedMessage

-0.89

 gyhoeddwyd

-0.81

 يتيمه

-0.79

ſicht

-0.77

Jeografia

-0.77

 unſer

-0.76

Datuak

-0.75

ſſung

-0.75

POSITIVE LOGITS

 Last

0.30

 Design

0.29

who

0.28

 origines

0.27

 identifiés

0.26

 Manager

0.26

design

0.26

kiu

0.25

 which

0.25

Activations Density 0.071%

key terms related to research methodology and results in scientific literature

determination and identification

No Comments

No Known Activations