INDEX

Explanations

references to audiences and their interactions with content

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

customers, readers, or audiences

np_acts-logits-general · gemini-2.0-flash

customer experience and feedback

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ValueStyle

-0.87

XmlAccessType

-0.75

PerformLayout

-0.64

AddTagHelper

-0.63

@[+][

-0.59

ReusableCell

-0.58

 ویکی‌پدی

-0.57

GenerationType

-0.57

InjectAttribute

-0.56

 PyTuple

-0.56

POSITIVE LOGITS

 Expectation

0.63

 Avatar

0.58

 expectation

0.57

 CONSUMER

0.56

 getItemCount

0.55

consumers

0.55

IENCE

0.55

 audiences

0.54

 consumidor

0.54

 setia

0.54

Activations Density 0.280%

references to audiences and their interactions with content

customers, readers, or audiences

customer experience and feedback

No Comments

No Known Activations