INDEX

Explanations

assignment operations in code

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

programming language code snippets

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

 الرياضيه

-0.42

-------

-0.35

adaptiveStyles

-0.34

 igång

-0.34



-0.33

aarrggbb

-0.33

 jScrollPane

-0.32

 contextLoads

-0.32

 concha

-0.32

enderror

-0.30

POSITIVE LOGITS

DockStyle

0.59

存于互联网档案馆

0.58

bootstrapcdn

0.53

 صوتيه

0.52

ikian

0.50

 telefónica

0.49

 Administrativna

0.49

makeConstraints

0.48

 Мексичка

0.48

pecabe

0.47

Activations Density 0.006%

assignment operations in code

programming language code snippets

No Comments

No Known Activations