INDEX

Explanations

mathematical notations and symbols typically used in scientific or technical contexts

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

Followed by the number 2

np_acts-logits-general · gemini-2.0-flash

"ep" followed by "2"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

dro

-0.53

 đấy

-0.48

thar

-0.46

cara

-0.45

imos

-0.45

caras

-0.44

ariya

-0.43

 Scene

-0.43

 Gall

-0.43

 Cara

-0.43

POSITIVE LOGITS

 AttributeSet

0.80

 صوتيه

0.78

kloped

0.77

DockStyle

0.75

 BoxDecoration

0.70

msgTypes

0.69

 المعرف

0.68

InstrumentedTest

0.67

 Bioaccumulative

0.66

žnost

0.66

Activations Density 0.962%

mathematical notations and symbols typically used in scientific or technical contexts

Followed by the number 2

"ep" followed by "2"

No Comments

No Known Activations