INDEX

Explanations

mathematical symbols and notations commonly used in mathematical proofs or formulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Географи

-0.67

GEBURTSDATUM

-0.52

__':

-0.50

WebServlet

-0.47

CppMethod

-0.47

AutoresizingMask

-0.46

trainable

-0.45

OptionsMenu

-0.45

használ

-0.45

idend

-0.45

POSITIVE LOGITS

 Wiktionnaire

0.67

 विश्वसनीयता

0.65

ArrowToggle

0.56

left

0.56

right

0.55

langle

0.54

 pinulongan

0.53

{|

0.53

endpush

0.52

lr

0.52

Activations Density 0.166%

mathematical symbols and notations commonly used in mathematical proofs or formulations

No Comments

No Known Activations