INDEX

Explanations

references to variables and parameters in mathematical or programming contexts

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

numbers, punctuation, articles

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

 nahilalakip

-0.47

tvguidetime

-0.44

OGND

-0.44

setViewportView

-0.44

تقاوى

-0.43

rungsseite

-0.43

WithIOException

-0.42

StoryboardSegue

-0.42

 disambiguazione

-0.41

 мәкал

-0.41

POSITIVE LOGITS

 دست

0.44

 Withers

0.42

 Zustimmung

0.42

 Hildebrand

0.41

findFirst

0.41

 Investi

0.41

 useContext

0.41

 LIABLE

0.40

 henvisninger

0.40

 adquisición

0.40

Activations Density 0.159%

references to variables and parameters in mathematical or programming contexts

numbers, punctuation, articles

No Comments

No Known Activations