INDEX

Explanations

use of the word "something" or "nothing"

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.22.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.22.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

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

Embeds

IFrame

Link

Negative Logits

 ivelany

-0.51

TagHelpers

-0.51

entang

-0.46

warded

-0.45

łucha

-0.45

kannya

-0.43

مدة

-0.43

Datuak

-0.43

DTD

-0.43

ätter

-0.42

POSITIVE LOGITS

 else

1.97

Else

1.29

 Else

1.22

 ELSE

1.19

else

1.17

ELSE

1.05

 resembling

0.91

 happening

0.88

 happened

0.83

 besides

0.81

Activations Density 0.976%

use of the word "something" or "nothing"

No Known Activations