INDEX

Explanations

instances of interactions or communications related to organizational or procedural contexts

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

énario

-0.60

 Мексичка

-0.57

zsche

-0.57

 doInBackground

-0.55

kegaard

-0.53

antMatchers

-0.53

basicConfig

-0.52

OpenHelper

-0.52

 Roskov

-0.51

érature

-0.51

POSITIVE LOGITS

 verbally

0.71

 fís

0.68

 physically

0.68

 orally

0.68

 Physically

0.65

 presencial

0.64

 verbal

0.62

 sẻ

0.61

 oral

0.60

 Oral

0.59

Activations Density 0.411%

instances of interactions or communications related to organizational or procedural contexts

No Comments

No Known Activations