INDEX

Explanations

information about applications and uses across various industries

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

"uses" or "applications"

np_acts-logits-general · gemini-2.0-flash

uses and applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Personendaten

-0.62

 Numerade

-0.60

ValueStyle

-0.58

aktery

-0.57

 المعيارى

-0.54

ikou

-0.54

myra

-0.51

UAWEI

-0.49

MemoryWarning

-0.48

퀀

-0.48

POSITIVE LOGITS

 usage

1.89

 uses

1.88

 Uses

1.82

 usages

1.72

use

1.68

Uses

1.66

 Usage

1.63

 applications

1.61

usage

1.55

 USES

1.52

Activations Density 0.811%

information about applications and uses across various industries

"uses" or "applications"

uses and applications

No Comments

No Known Activations