INDEX

Explanations

references to geometric shapes, particularly squares

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Personensuche

-1.09

onAttach

-0.77

 Nevis

-0.74

antd

-0.69

omitempty

-0.67

TagMode

-0.64

 Govt

-0.64

dubbo

-0.63

---*/

-0.62

MenuInflater

-0.62

POSITIVE LOGITS

 square

2.38

 Square

2.37

 SQUARE

2.29

 squares

2.27

Square

2.23

SQUARE

2.09

square

2.07

 Squares

2.07

Squares

2.01

squares

1.84

Activations Density 0.051%

references to geometric shapes, particularly squares

No Comments

No Known Activations