INDEX

Explanations

phrases that indicate intentions or actions, particularly starting with "To"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

CppMethod

-0.52

 endregion

-0.51

 protoimpl

-0.48

 Bintang

-0.47

 OMITBAD

-0.45

 AssemblyVersion

-0.44

endphp

-0.43

/*

-0.43

Sú

-0.42

 виправивши

-0.41

POSITIVE LOGITS

To

0.86

To

0.79

 Чтобы

0.59

Чтобы

0.58

 Để

0.57

Для

0.57

 Для

0.57

Để

0.54

するには

0.53

要想

0.49

Activations Density 0.097%

phrases that indicate intentions or actions, particularly starting with "To"

No Comments

No Known Activations