INDEX

Explanations

programming-related technical terms and class definitions

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

PATH NGX_SBIN_PATH

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

RegressionTest

-0.50

RenderAtEndOf

-0.49

➟

-0.45

Демографія

-0.44

itinéraire

-0.44

TagMode

-0.44

 للمعارف

-0.42

 informée

-0.42

Espèce

-0.41

 Autorizaciones

-0.41

POSITIVE LOGITS

StandardCharsets

0.68

oneofs

0.60

IntoConstraints

0.56

 propOrder

0.55

SerializedName

0.48

therin

0.47

URLException

0.46

XmlAccessorType

0.44

/***/

0.44

styleable

0.44

Activations Density 0.014%

programming-related technical terms and class definitions

PATH NGX_SBIN_PATH

No Comments

No Known Activations