INDEX

Explanations

terms related to partnerships and collaboration

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

évaluateur

-0.90

 autorytatywna

-0.85

MLLoader

-0.78

 referenties

-0.77

úi

-0.75

 Blob

-0.74

ollectionView

-0.74

ยนต์

-0.71

Zubereitung

-0.71

 clique

-0.70

POSITIVE LOGITS

 Partners

1.20

Partners

1.13

partners

1.04

 partners

1.02

 Partner

1.02

 PARTNER

1.00

Partner

0.94

 partner

0.92

 PARTNERS

0.91

spartner

0.85

Activations Density 0.007%

terms related to partnerships and collaboration

No Comments

No Known Activations