INDEX

Explanations

instances of function definitions and comments in programming code

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

code and keywords

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

Spoljašnje

-0.56

baguna

-0.47

 Мексичка

-0.46

༘

-0.43

pausal

-0.43

 Савезне

-0.42

 SwitchCompat

-0.42

 beginnetje

-0.41

ArrowToggle

-0.41

󠁮

-0.41

POSITIVE LOGITS

 '\\;'

0.48

 BytesLike

0.43

EndInit

0.43

bibitem

0.42

طلحات

0.39

KommentareTeilen

0.39

üyada

0.39

UpdateCommand

0.37

OGND

0.37

'}),

0.37

Activations Density 0.002%

instances of function definitions and comments in programming code

code and keywords

No Comments

No Known Activations