INDEX

Explanations

phrases related to the functioning and operation of systems or products

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

operating, functioning, working

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 invitation

-0.41

“

-0.40

 select

-0.39

УДК

-0.39

Kot

-0.38

 invites

-0.38

cer

-0.38

 image

-0.38

 pick

-0.37

 flag

-0.37

POSITIVE LOGITS

 funcionamento

0.82

functioning

0.80

 fonctionnement

0.80

 funcionamiento

0.78

 functioning

0.77

 funzionamento

0.71

 fonctionner

0.69

 hoạt

0.63

 funcionar

0.63

 Functionality

0.61

Activations Density 0.047%

phrases related to the functioning and operation of systems or products

operating, functioning, working

No Comments

No Known Activations