INDEX

Explanations

terms related to legal indictments and charges

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

FormItem

-0.64

Portail

-0.60

 Roskov

-0.59

voltaic

-0.59

schild

-0.59

 Ludlow

-0.57

 Clas

-0.57

 Gregor

-0.57

 Rooms

-0.57

ristas

-0.57

POSITIVE LOGITS

 indictment

1.32

 indict

1.25

 indicted

1.13

 AspNetCore

0.72

 Suecia

0.66

IsMutable

0.66

 Vance

0.65

 bougies

0.63

 doInBackground

0.63

 urbanas

0.63

Activations Density 0.006%

terms related to legal indictments and charges

No Comments

No Known Activations