INDEX

Explanations

terms related to dependency and variability in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

PerformLayout

-0.49

Démographie

-0.47

prefixer

-0.46

CardBody

-0.45

addCriterion

-0.44

DeleteBehavior

-0.42

 разве

-0.41

WebElementEntity

-0.41

upné

-0.40

bado

-0.40

POSITIVE LOGITS

 depending

1.18

 depends

1.17

depending

1.08

 Depends

1.05

Depends

1.02

depends

0.99

 Depending

0.99

Depending

0.98

 dependiendo

0.95

 varies

0.90

Activations Density 0.518%

terms related to dependency and variability in different contexts

No Comments

No Known Activations