INDEX

Explanations

terms related to statistical concepts, particularly "mean" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ContentAsync

-0.84

awtextra

-0.80

Aiheesta

-0.79

AntiForgeryToken

-0.78

ChildScrollView

-0.78

ViewFeatures

-0.74

prefixer

-0.70

tanleria

-0.69

XFF

-0.66

tagHelper

-0.66

POSITIVE LOGITS

tioned

0.76

urement

0.60

MEAN

0.59

 MEAN

0.57

 litté

0.57

er

0.56

ScreenWidth

0.55

cillor

0.55

 Means

0.54

WHILE

0.53

Activations Density 0.087%

terms related to statistical concepts, particularly "mean" and its variations

No Comments

No Known Activations