INDEX

Explanations

references to older individuals or things

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

<em>

-0.78

“

-0.76

ing

-0.69

</em>

-0.68

‘

-0.68

 than

-0.65

↵↵

-0.63

en

-0.63

Pe

-0.60

POSITIVE LOGITS

ſelves

1.33

 Houſe

1.31

 Monfieur

1.29

ſelf

1.27

 Anſ

1.25

 Diſ

1.24

 Majefty

1.24

 iſt

1.23

 myſelf

1.23

Efq

1.19

Activations Density 0.007%

references to older individuals or things

No Comments

No Known Activations