INDEX

Explanations

terms related to statistical analysis and data normalization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

complexType

-0.45

outSlope

-0.43

getResultList

-0.43

 Scalars

-0.42

featureID

-0.41

ValueGenerated

-0.40

 attacker

-0.40

ghalaya

-0.40

❸

-0.39

 anastom

-0.38

POSITIVE LOGITS

esModule

0.48

 normalization

0.47

 standar

0.47

 standardization

0.43

 mijne

0.43

boutin

0.40

 Standardization

0.39

Normalization

0.39

 zijne

0.39

aarrggbb

0.38

Activations Density 0.875%

terms related to statistical analysis and data normalization

No Comments

No Known Activations