INDEX

Explanations

terms related to distraction and distractions

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OGND

-0.93

 calendriers

-0.87

 ExecuteAsync

-0.82

HideFlags

-0.82

 AssemblyCulture

-0.77

 JpaRepository

-0.75

styleUrls

-0.73

 peindre

-0.73

NSYLVANIA

-0.73

+#+

-0.69

POSITIVE LOGITS

 distraction

1.43

 distractions

1.38

 distra

1.32

 distract

1.28

 distracting

1.25

 distracted

1.24

 Distra

1.24

 divert

0.93

 DISTR

0.91

 diversion

0.89

Activations Density 0.002%

terms related to distraction and distractions

No Comments

No Known Activations

terms related to distraction and distractions

No Comments

No Known Activations