INDEX

Explanations

terms related to geometric shapes, particularly squares and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 loadData

-0.54

DID

-0.54

mapStateToProps

-0.50

最快更新

-0.49

 Nostalgia

-0.47

!<

-0.46

Naissance

-0.46

 Riti

-0.45

czas

-0.45

helin

-0.44

POSITIVE LOGITS

 rectangle

0.71

 SQUARE

0.70

 square

0.65

 Square

0.64

SQUARE

0.60

quare

0.59

 diamond

0.59

 triangle

0.56

Square

0.55

square

0.54

Activations Density 0.664%

terms related to geometric shapes, particularly squares and their properties

No Comments

No Known Activations