INDEX

Explanations

metrics for assessing validity, reliability, and responsiveness in research data

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

Quantifying measurement, extent, or degree

np_acts-logits-general · gemini-2.0-flash

degree, amount, and distance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 TextAppearance

-0.48

 encantan

-0.47

cycline

-0.47

isiä

-0.46

 piccoli

-0.45

 dépasse

-0.45

HandlerContext

-0.45

 farlo

-0.44

 campanha

-0.44

 bellissimo

-0.42

POSITIVE LOGITS

 amount

1.50

how

1.47

 degree

1.45

どれだけ

1.29

 extent

1.25

degree

1.21

amount

1.18

 Degree

1.17

 hoeveel

1.16

 DEGREE

1.13

Activations Density 0.726%

metrics for assessing validity, reliability, and responsiveness in research data

Quantifying measurement, extent, or degree

degree, amount, and distance

No Comments

No Known Activations