INDEX

Explanations

visibility states and actions related to showing and hiding elements in an interface

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

약

-0.59

τεύ

-0.52

 intptr

-0.52

की

-0.50

yntaxException

-0.50

stdint

-0.47

RepeatedField

-0.47

향

-0.47

barrel

-0.47

co

-0.47

POSITIVE LOGITS

 visibility

0.77

 Visibility

0.74

setVisibility

0.73

visibility

0.71

 isShow

0.66

VISIBLE

0.65

 presence

0.63

 OnEnable

0.63

ToShow

0.63

visible

0.62

Activations Density 0.125%

visibility states and actions related to showing and hiding elements in an interface

No Comments

No Known Activations