INDEX

Explanations

phrases related to placing or positioning something

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

DockStyle

-1.08

 Waray

-1.00

AutoScale

-0.91

ValueStyle

-0.91

archiviato

-0.85

tagext

-0.84

AnchorStyles

-0.82

 Armada

-0.82

 GenerationType

-0.81

Zunanje

-0.81

POSITIVE LOGITS

put

1.52

Put

1.52

Put

1.47

 Puts

1.40

PUT

1.38

put

1.36

 puts

1.34

 putting

1.28

putting

1.23

 Putting

1.22

Activations Density 0.117%

phrases related to placing or positioning something

No Known Activations