INDEX

Explanations

elements discussing image and audio quality in media

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

Image sharpness and clarity

np_acts-logits-general · gemini-2.0-flash

image sharpness and blurriness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

transQ

-0.44

openzeppelin

-0.39

ittarius

-0.39

 jsPsych

-0.37

SequentialGroup

-0.32

weck

-0.32

Biographie

-0.32

 autorytatywna

-0.31

AndroidJUnit

-0.31

 dangereux

-0.30

POSITIVE LOGITS

 sharpness

1.02

 crisp

0.96

 clarity

0.96

 sharper

0.86

 clearer

0.84

 blurry

0.82

 detail

0.81

 resolution

0.81

 clearest

0.79

 sharpen

0.78

Activations Density 0.413%

elements discussing image and audio quality in media

Image sharpness and clarity

image sharpness and blurriness

No Comments

No Known Activations