INDEX

Explanations

technical references related to resources and studies in a scientific context

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

references and studies

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

transQ

-0.94

 nakalista

-0.87

 ویکی‌پدی

-0.83

 وتسجيلات

-0.83

 незавершена

-0.81

 kasarigan

-0.79

migrationBuilder

-0.76



-0.74

⮕

-0.73

 ligiloj

-0.73

POSITIVE LOGITS

↵↵

0.27

adhé

0.26

Both

0.26

Descripción

0.26

 Both

0.26

ArgsConstructor

0.26

半天

0.26

udi

0.26

ما

0.25

läufe

0.25

Activations Density 0.369%

technical references related to resources and studies in a scientific context

references and studies

No Comments

No Known Activations