INDEX

Explanations

words expressing complexity and qualities of experiences or objects

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

ending in "-ive" or "-plex"

np_acts-logits-general · gemini-2.0-flash

qualities and characteristics

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

 تضيفلها

-0.73

LookAnd

-0.71

 betweenstory

-0.69

WithIOException

-0.67

GEBURTSDATUM

-0.66

Tikang

-0.64

AndEndTag

-0.63

tagHelperRunner

-0.62

 anún

-0.60

 समीक्षाएं

-0.59

POSITIVE LOGITS

 enough

1.01

ly

0.71

enough

0.61

 insofar

0.59

and

0.58

 للغاية

0.56

ness

0.55

viewWillAppear

0.55

 geworden

0.54

 though

0.52

Activations Density 0.850%

words expressing complexity and qualities of experiences or objects

ending in "-ive" or "-plex"

qualities and characteristics

No Comments

No Known Activations