INDEX

Explanations

equality symbols in code or textual representations

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

user assignment or condition

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

بيوتر

-0.49

wnicy

-0.43

eterangan

-0.40

ニュアル

-0.38

 BoxDecoration

-0.38

 Architektur

-0.37

pushFollow

-0.36

 cortos

-0.36

 sencillos

-0.36

 pemberian

-0.35

POSITIVE LOGITS

httphttps

0.70

 Wicidata

0.65

==

0.63

==

0.61

])))

0.57

 OnEnable

0.56

])));

0.56

dafx

0.54

">//

0.54

/**

0.53

Activations Density 0.026%

equality symbols in code or textual representations

user assignment or condition

No Comments

No Known Activations