INDEX

Explanations

terminology related to discipline and disciplinary actions

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

BrowserModule

-0.63

tilde

-0.62

Bbb

-0.62

 بالح

-0.61

 Atwood

-0.60

 Sander

-0.60

 Hage

-0.60

orter

-0.59

ostom

-0.59

Wau

-0.57

POSITIVE LOGITS

 Discipline

1.70

 disciplines

1.52

 Discipl

1.51

Discipline

1.49

 discipline

1.48

Discipl

1.45

discipline

1.44

 DISCIP

1.40

disciplinary

1.34

discipl

1.34

Activations Density 0.003%

terminology related to discipline and disciplinary actions

No Comments

No Known Activations