INDEX

Explanations

references to medical procedures or protocols

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

Preceding section or figure references

np_acts-logits-general · gemini-2.0-flash

citations and references

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 مشين

-0.80

Hentet

-0.73

 kasarigan

-0.70

\{\\

-0.62

addContainerGap

-0.60

цездатний

-0.59

<bos>

-0.59

expandindo

-0.56

Portály

-0.56

 externi

-0.55

POSITIVE LOGITS

0.69

penia

0.64

Aktualisiert

0.57

0.56

bootstrapcdn

0.56

 illetve

0.56

öße

0.55

respectively

0.51

aughey

0.51

$-

0.51

Activations Density 0.978%

references to medical procedures or protocols

Preceding section or figure references

citations and references

No Comments

No Known Activations