INDEX

Explanations

references to the term 'var' and its variations in the context of statistical analysis or study findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

CloseOperation

-0.70

VersionUID

-0.59

TagHelper

-0.59

ollectionView

-0.58

 برانيه

-0.57

@[+][

-0.57

ématiques

-0.57

udder

-0.55

Ecotoxicity

-0.54

lijah

-0.54

POSITIVE LOGITS

fvar

0.81

argout

0.69

 intptr

0.68

VAR

0.67

 Vars

0.64

 Vara

0.64

 StringVar

0.63

 Wrang

0.62

VAR

0.61

ftig

0.61

Activations Density 0.175%

references to the term 'var' and its variations in the context of statistical analysis or study findings

No Comments

No Known Activations