INDEX

Explanations

technical terminology related to flexibility and layout in design

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

"flex" and its variations

np_acts-logits-general · gemini-2.0-flash

flex followed by specific words

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

 TestBed

-0.85

 Chwiliwch

-0.82

脚注の使い方

-0.81

MessageOf

-0.81

sizeCache

-0.80

OGND

-0.79

HostException

-0.78

Rüyada

-0.77

 ExecuteAsync

-0.76

 propOrder

-0.76

POSITIVE LOGITS

Flex

1.04

 Flex

1.04

 flex

1.01

 FLEX

0.99

FLEX

0.96

flex

0.92

 flexing

0.81

 flexibles

0.81

 Flexible

0.78

 flexibility

0.78

Activations Density 0.117%

technical terminology related to flexibility and layout in design

"flex" and its variations

flex followed by specific words

No Comments

No Known Activations