INDEX

Explanations

words related to police, law enforcement, and court proceedings

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.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.24.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

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

Embeds

IFrame

Link

Negative Logits

 famously

-0.61

Tembelea

-0.57

his

-0.56

TestingModule

-0.56

 cheeky

-0.55

>{{

-0.54

Così

-0.54

 symbolically

-0.52

 exec

-0.52

 midwives

-0.52

POSITIVE LOGITS

 sospe

0.63

 Deputies

0.62

 Officers

0.60

 occupants

0.60

 mukaan

0.58

 occupant

0.56

 grammi

0.56

 vectorielles

0.56

 femininas

0.56

 deputies

0.55

Activations Density 1.113%

words related to police, law enforcement, and court proceedings

No Known Activations