INDEX

Explanations

database table names and their definitions

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

Negative Logits

 Проци

-0.78

 مرئيه

-0.77

 Pilate

-0.72

 المعيارى

-0.69

Numerology

-0.68

 itſelf

-0.67

ContentLoaded

-0.67

 iſt

-0.65

vdash

-0.65

 juſ

-0.65

POSITIVE LOGITS

 otomatig

0.44

 durar

0.42

имо

0.41

cheinend

0.41

DbContext

0.41

 تاب

0.41

Dra

0.40

疫情

0.39

tra

0.39

 contact

0.39

Activations Density 0.005%

database table names and their definitions

No Known Activations