INDEX

Explanations

references to recreational facilities, particularly pools and aquatic features

oai_token-act-pair · gpt-4o-mini Triggered by @bot

amenities and features of recreational facilities, particularly pools and water attractions.

oai_token-act-pair · claude-4-5-haiku Triggered by @emiglarou

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PathVariable

-0.40

oneofs

-0.39

lingua

-0.39

DrawerToggle

-0.38

 nakalista

-0.38

 propOrder

-0.38

nocache

-0.38

Espèce

-0.38

 Catawiki

-0.37

 ActionListener

-0.36

POSITIVE LOGITS

 swimming

2.08

 pool

1.88

 swim

1.85

 Swimming

1.84

Swimming

1.78

 swimmers

1.77

swimming

1.73

 Swim

1.69

 zwem

1.66

 Pool

1.66

Activations Density 0.114%

references to recreational facilities, particularly pools and aquatic features

amenities and features of recreational facilities, particularly pools and water attractions.

No Comments

No Known Activations