INDEX

Explanations

references to scientific methods and parameters in research

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

after articles or prepositions

np_acts-logits-general · gemini-2.0-flash

grandmother said that

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

 Италијани

-0.54

WithIOException

-0.53

ArrowToggle

-0.53

PRNewswire

-0.50

別

-0.48

 Geste

-0.47

UNIDENTIFIED

-0.46

 ligiloj

-0.46

奥

-0.46

龱

-0.46

POSITIVE LOGITS

ArgsConstructor

1.12

$.

0.77

Personendaten

0.75

NUMX

0.75

 Signalez

0.74

endphp

0.73

 برانيه

0.73

 NSCoder

0.72

CloseOperation

0.72

 pinulongan

0.71

Activations Density 1.662%

references to scientific methods and parameters in research

after articles or prepositions

grandmother said that

No Comments

No Known Activations