INDEX

Explanations

terms related to variables and their variations in data analysis

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

Tokens starting with "Vari" or "var"

np_acts-logits-general · gemini-2.0-flash

variances, variable names, varieties

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

ématiques

-0.51

oredCriteria

-0.50

VersionUID

-0.48

cps

-0.47

LayoutStyle

-0.45

Bio

-0.45

ześnie

-0.45

 gana

-0.44

etan

-0.44

م

-0.43

POSITIVE LOGITS

fvar

0.76

IUrlHelper

0.73

verwijspagina

0.73

 intptr

0.71

 Vari

0.71

VAR

0.67

Tracce

0.67

ieties

0.64

 alé

0.64

Vari

0.63

Activations Density 0.264%

terms related to variables and their variations in data analysis

Tokens starting with "Vari" or "var"

variances, variable names, varieties

No Comments

No Known Activations