INDEX

Explanations

instances of specific numerical values or quantities, particularly in a technical or scientific context

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

names after 'to' in patents

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

pyplot

-0.50

دانشنامهٔ

-0.49

 normalidad

-0.47

RegressionTest

-0.45

 excelencia

-0.45

RenderAtEndOf

-0.44

новниш

-0.44

 estekak

-0.44

 equipamiento

-0.43

exitRule

-0.42

POSITIVE LOGITS

Personendaten

0.79

 disambiguazione

0.58

rawDesc

0.48

 AssemblyCompany

0.43

Author

0.43

author

0.42

 author

0.42

Genie

0.42

 genie

0.42

diffusion

0.41

Activations Density 0.000%

instances of specific numerical values or quantities, particularly in a technical or scientific context

names after 'to' in patents

No Comments

No Known Activations