INDEX

Explanations

details related to pricing and fees

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

costs and fees

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

webElementXpaths

-0.61

ValueStyle

-0.59

 للمعارف

-0.59

 nonUne

-0.52

aarrggbb

-0.51

 GenerationType

-0.50

GEBURTS

-0.50

recated

-0.49

RegressionTest

-0.49

expandindo

-0.49

POSITIVE LOGITS

sprechend

0.35

 ویکی‌پدیای

0.34

idoscope

0.33

 kada

0.33

ActionPerformed

0.32

 الخير

0.32

acad

0.31

gjenge

0.31

using

0.30

 varies

0.30

Activations Density 0.025%

details related to pricing and fees

costs and fees

No Comments

No Known Activations