INDEX

Explanations

references to specific data and coding syntax related to programming or technology

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

programming code and technical terms

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

rungsseite

-0.39

govine

-0.38

 NSCoder

-0.35

☚

-0.35



-0.35

 препратки

-0.34

دانشنامهٔ

-0.34

 koos

-0.34

startActivity

-0.33

 فريبيس

-0.33

POSITIVE LOGITS

"]();

0.53

MLLoader

0.53

 الحره

0.51

ReusableCell

0.50

("")]

0.46

Personensuche

0.46

ViewImports

0.45

 AssemblyVersion

0.44

')")

0.44

 Paglinawan

0.43

Activations Density 0.022%

references to specific data and coding syntax related to programming or technology

programming code and technical terms

No Comments

No Known Activations