INDEX

Explanations

programming terms related to APIs and their status indicators

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

API documentation and export directives

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

IsContent

-0.46

ChildScrollView

-0.45

SequentialGroup

-0.43

 Sélectionnez

-0.38

FormBuilder

-0.38

 Organización

-0.37

CloseOperation

-0.37

principalColumn

-0.35

 käytt

-0.34

Bronnen

-0.33

POSITIVE LOGITS

vode

0.60

 ujednoznacz

0.52

 disambiguazione

0.51

astéroïdes

0.51

ByVersion

0.48

SuppressLint

0.47

iguar

0.47

rildi

0.46

httphttps

0.46

nodoc

0.45

Activations Density 0.025%

programming terms related to APIs and their status indicators

API documentation and export directives

No Comments

No Known Activations