INDEX

Explanations

technical terms and measurements related to numerical accuracy and significant figures in data

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

significant figures and decimal places

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

ftagPool

-0.77

 lenker

-0.60

httphttps

-0.54

IBAction

-0.51

DropColumn

-0.51

SequentialGroup

-0.49

MLLoader

-0.49

URLException

-0.49

̍t

-0.48

RetentionPolicy

-0.47

POSITIVE LOGITS

 ModelExpression

0.42

 accuracy

0.38

 accurate

0.34

 guarn

0.32

 Qualität

0.32

accuracy

0.32

精度

0.31

vyšší

0.31

MigrationBuilder

0.30

hängigkeit

0.29

Activations Density 0.080%

technical terms and measurements related to numerical accuracy and significant figures in data

significant figures and decimal places

No Comments

No Known Activations