INDEX

Explanations

references to employment and company information

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

company and employer

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

findpost

-0.54

:✨

-0.48

Obrázky

-0.46

Microkernel

-0.45

featureID

-0.44

 ویکی‌پدی

-0.43

 MainAxisSize

-0.43

jeeling

-0.43

opla

-0.43

 ویکی‌آمباردا

-0.42

POSITIVE LOGITS

 company

0.68

 employer

0.58

 Company

0.58

 corporation

0.57

 employee

0.54

 empresa

0.54

employer

0.52

 organisation

0.52

company

0.51

 EMPLOY

0.51

Activations Density 0.046%

references to employment and company information

company and employer

No Comments

No Known Activations