INDEX

Explanations

terms related to keys and layouts in programming or configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 utafitiHapana

-0.57

бва

-0.56

<bos>

-0.56

ViewChild

-0.55

cienti

-0.55

 nonatomic

-0.54

SOUNDBITE

-0.54

declare

-0.53

 متحده

-0.52

 للمعارف

-0.51

POSITIVE LOGITS

 layout

0.89

Layout

0.88

 Layout

0.79

 Obrador

0.76

layout

0.75

 समीक्षाओं

0.74

 layouts

0.74

 LAYOUT

0.72

mbic

0.70

 design

0.70

Activations Density 0.147%

terms related to keys and layouts in programming or configurations

No Comments

No Known Activations