INDEX

Explanations

specific terms and concepts related to various subjects, including scientific terms, health conditions, and elements of media and performance

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

after capitalized words

np_acts-logits-general · gemini-2.0-flash

radial nerve blocks

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 للاسماء

-0.66

 فريبيس

-0.64

 ErrIntOverflow

-0.63

 Italijanski

-0.63

Rptr

-0.62

دانشنامهٔ

-0.61

 gyhoeddwyd

-0.60

وروبا

-0.58

IntoConstraints

-0.58

 CreateTagHelper

-0.57

POSITIVE LOGITS

httphttps

0.33

Vezi

0.28

 inauguración

0.25

ようになりました

0.25

 alguno

0.24

 alguna

0.24

Store

0.24

 algún

0.24

 supuesto

0.24

 क्ल

0.23

Activations Density 0.715%

specific terms and concepts related to various subjects, including scientific terms, health conditions, and elements of media and performance

after capitalized words

radial nerve blocks

No Comments

No Known Activations