INDEX

Explanations

dimensions and styles related to UI elements in a web or app layout context

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

Tokens within bracketed image file names

np_acts-logits-general · gemini-2.0-flash

android height wrap_content

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

oredCriteria

-0.65

 вікі

-0.53

FieldBuilder

-0.52

#+#

-0.49

Referencie

-0.48

 eventdata

-0.47

 บาท

-0.46

 EconPapers

-0.46

addLast

-0.45

Expose

-0.45

POSITIVE LOGITS

 height

0.74

 HEIGHT

0.64

height

0.62

HEIGHT

0.61

 intStringLen

0.60

 ſmall

0.57

 مرئيه

0.56

/\.

0.56

 Height

0.55

 GIPHY

0.55

Activations Density 0.089%

dimensions and styles related to UI elements in a web or app layout context

Tokens within bracketed image file names

android height wrap_content

No Comments

No Known Activations