INDEX

Explanations

references to mathematical libraries and frameworks

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

IsContent

-0.77

TagMode

-0.68

Geplaatst

-0.67

prefixer

-0.59

//

-0.56

aspectj

-0.55

AutoScaleMode

-0.54

 <<<<<<<<<<<<<<

-0.53

aternary

-0.53

 שוליים

-0.53

POSITIVE LOGITS

 препратки

0.72

 متعلقه

0.67

 saites

0.63

ährend

0.56

principalTable

0.55

Personensuche

0.54

 iſt

0.53

Autoritní

0.52

 Photographie

0.51

 đoàn

0.51

Activations Density 0.300%

references to mathematical libraries and frameworks

No Comments

No Known Activations