INDEX

Explanations

elements related to programming structures and objects in code

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

programming imports and progress indicators

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

 kaarangay

-0.68

 EconPapers

-0.58

contentLoaded

-0.54

optionalTypeArgs

-0.54

Tikang

-0.53

oredCriteria

-0.52

хьтан

-0.52

 noDo

-0.51

-------

-0.51

存于互联网档案馆

-0.48

POSITIVE LOGITS

 tqdm

1.27

tq

0.57

bar

0.47

WaitGroup

0.42

 mecánico

0.41

ProgressBar

0.40

 المعرف

0.40

 Iterator

0.39

AddRange

0.39

bar

0.39

Activations Density 0.001%

elements related to programming structures and objects in code

programming imports and progress indicators

No Comments

No Known Activations

elements related to programming structures and objects in code

programming imports and progress indicators

No Comments

No Known Activations