INDEX

Explanations

terms related to gauge dependence and parametric definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Diwedd

-0.60

SpringBootTest

-0.51

 Mercure

-0.51

 superiori

-0.47

Pattern

-0.47

 ostavi

-0.46

 titolata

-0.46

")));

-0.46

 rivol

-0.45

fek

-0.45

POSITIVE LOGITS

Geplaatst

0.68

 MenuView

0.64

 Interpretation

0.64

 interpretations

0.63

interprétation

0.63

 interpretation

0.63

 interpr

0.62

 INTERPRET

0.62

Interpretation

0.60

interpretation

0.59

Activations Density 0.768%

terms related to gauge dependence and parametric definitions

No Comments

No Known Activations