INDEX

Explanations

phrases related to customization or personalization features in applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

原始内容存档于

-0.67

出版年

-0.66

Tikang

-0.65

LikeLike

-0.61

ymce

-0.59

sidemargin

-0.57

saraba

-0.56

AxisAlignment

-0.54

wiście

-0.53

LikeLiked

-0.53

POSITIVE LOGITS

 <>",

0.71

RTLD

0.66

 faltar

0.57

enderror

0.55

 joga

0.52

mány

0.52

badlogic

0.52

contains

0.51

 phun

0.51

ThemeOverlay

0.50

Activations Density 0.136%

phrases related to customization or personalization features in applications

No Comments

No Known Activations