INDEX

Explanations

notations and symbols related to mathematical sets and graphs

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

Variables in mathematical expressions

np_acts-logits-general · gemini-2.0-flash

$ followed by symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

TagMode

-0.92

 Савезне

-0.85

__':

-0.84

 ujednoznacz

-0.84

 propOrder

-0.81

afficheront

-0.79

__":

-0.74

IUrlHelper

-0.71

abstractmethod

-0.69

KommentareTeilen

-0.67

POSITIVE LOGITS

0.47

is

0.47

 belongs

0.46

égio

0.46

0.44

 kaynağından

0.44

 meets

0.43

 must

0.42

Activations Density 2.151%

notations and symbols related to mathematical sets and graphs

Variables in mathematical expressions

$ followed by symbols

No Comments

No Known Activations