INDEX

Explanations

references to circular shapes and related geometrical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 للمعارف

-0.78

 Sted

-0.74

ntax

-0.73

MAV

-0.73

########.

-0.72

<thead>

-0.71

 Nast

-0.70

MAV

-0.67

rophoto

-0.67

 Mahi

-0.65

POSITIVE LOGITS

 circles

1.51

 circle

1.50

 Circle

1.45

 CIRCLE

1.43

Circles

1.43

 Circles

1.40

Circle

1.36

 ring

1.35

circle

1.30

circles

1.30

Activations Density 0.257%

references to circular shapes and related geometrical terms

No Comments

No Known Activations