INDEX

Explanations

inquiries related to complex or technical concepts

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

Punctuations: commas, question marks

np_acts-logits-general · gemini-2.0-flash

"or" in multiple languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 surla

-0.48

 ویکی‌پدیا

-0.44

 Lopes

-0.41

ENODE

-0.40

ruptedException

-0.39

 doInBackground

-0.39

 onOptions

-0.39

 Schulte

-0.39

metis

-0.38

 incontinence

-0.38

POSITIVE LOGITS

or

1.10

 или

0.91

或是

0.85

 hoặc

0.84

 یا

0.81

 alebo

0.80

 atau

0.79

 oppure

0.79

หรือ

0.78

 หรือ

0.77

Activations Density 0.688%

inquiries related to complex or technical concepts

Punctuations: commas, question marks

"or" in multiple languages

No Comments

No Known Activations