INDEX

Explanations

technical terms and definitions related to programming constructs

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

macro definitions

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

IBarButtonItem

-0.46

PreferredItem

-0.44

RTLI

-0.41

TagHelper

-0.41

TestingModule

-0.40

webElementXpaths

-0.39

HasAnnotation

-0.39

BufferException

-0.37

TagMode

-0.36

Према

-0.35

POSITIVE LOGITS

期刊论文

0.59

endphp

0.55

__(/*!

0.52

 <<<<<<<<<<<<<<

0.48

InlineData

0.47

...)

0.46

 ...)

0.45

INGO

0.45

seamnă

0.44

 htons

0.43

Activations Density 0.135%

technical terms and definitions related to programming constructs

macro definitions

No Comments

No Known Activations