INDEX

Explanations

mathematical expressions or notation related to graph theory

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

-0.84

 MacKenzie

-0.78

-0.68

Kenzie

-0.67

ه

-0.66

-0.65

 Aragón

-0.63

-0.59

т

-0.59

POSITIVE LOGITS

 Wiktionnaire

1.02

gallo

0.92

="{{$

0.88

VIAF

0.88

 unknownFields

0.84

 dépens

0.83

 Werth

0.81

 Jaros

0.80

UserScript

0.79

doPost

0.78

Activations Density 0.009%

mathematical expressions or notation related to graph theory

No Comments

No Known Activations