INDEX

Explanations

references to plates and dishes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 onCancelled

-0.80

 ")";

-0.71

</thead>

-0.67

unmodifiable

-0.67

 Aquila

-0.66

près

-0.65

']));

-0.64

vaila

-0.64

Egy

-0.64

/>}

-0.63

POSITIVE LOGITS

 plates

1.52

 Plate

1.50

 Plates

1.49

 plate

1.38

Plate

1.38

Plates

1.37

 PLATE

1.37

 PLATES

1.36

plate

1.30

PLATE

1.25

Activations Density 0.121%

references to plates and dishes in various contexts

No Comments

No Known Activations