INDEX

Explanations

terms related to electrical windings and their configurations

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

 immédi

-0.82

 للمعارف

-0.82

rzez

-0.79

 Striker

-0.79

 indisponible

-0.78

 שוליים

-0.77

 Latham

-0.77

 kube

-0.73

 Beacons

-0.72

Tuk

-0.72

POSITIVE LOGITS

 Winding

1.29

 winding

1.23

winding

1.22

 windings

1.09

 Winder

1.02

 unwind

0.84

Reel

0.80

 reels

0.77

 Reel

0.75

巻

0.75

Activations Density 0.016%

terms related to electrical windings and their configurations

No Comments

No Known Activations