INDEX

Explanations

references to numerical data and counts related to various contexts

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

Followed by a number or count

np_acts-logits-general · gemini-2.0-flash

number and count

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

kegaard

-0.54

:✨

-0.48

pidou

-0.42

ModelForm

-0.41

itsch

-0.41

PhysRevD

-0.40

либо

-0.40

́ng

-0.40

toISOString

-0.39

mmHg

-0.39

POSITIVE LOGITS

 number

2.24

 count

2.02

number

1.92

 Anzahl

1.88

 تعداد

1.85

count

1.81

 numbers

1.81

 jumlah

1.79

Number

1.77

 aantal

1.76

Activations Density 1.862%

references to numerical data and counts related to various contexts

Followed by a number or count

number and count

No Comments

No Known Activations