INDEX

Explanations

technical specifications related to image dimensions and scaling in programming contexts

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

auto resize size

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

BeginInit

-0.47

EndInit

-0.42

Hentet

-0.42

 deputies

-0.42

__':

-0.41

Irm

-0.38

richTextPanel

-0.38

 deputy

-0.38

 Forward

-0.37

AddHtmlAttribute

-0.36

POSITIVE LOGITS

styleType

0.40

 continúas

0.39

 ngon

0.37

 bagay

0.36

InjectMocks

0.35

 endwhile

0.35

RTSC

0.35

 Objek

0.34

 zapo

0.34

 quelconque

0.34

Activations Density 0.011%

technical specifications related to image dimensions and scaling in programming contexts

auto resize size

No Comments

No Known Activations