INDEX

Explanations

references to downward movement or descent

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

 Magi

-0.88

Wib

-0.79

Erika

-0.76

 StringTokenizer

-0.73

 Erzb

-0.71

 вагі

-0.70

wig

-0.69

ⅰ

-0.69

 wigs

-0.69

 Puig

-0.69

POSITIVE LOGITS

 Down

1.45

 down

1.44

Down

1.41

Downs

1.35

 DOWN

1.32

downs

1.30

DOWN

1.25

 Downing

1.23

down

1.22

 downs

1.12

Activations Density 0.243%

references to downward movement or descent

No Comments

No Known Activations