INDEX

Explanations

occurrences of the word "defined" and related variations indicating the definition of terms or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Matth

-0.66

 Ninety

-0.63

ternut

-0.62

 Patro

-0.62

KommentareTeilen

-0.61

 subtree

-0.61

HomeAsUp

-0.61

ReusableCell

-0.60

borderSide

-0.60

bewerken

-0.60

POSITIVE LOGITS

 define

2.75

 defined

2.64

 defines

2.59

 defining

2.44

 Define

2.41

 Defined

2.37

 definition

2.35

defined

2.33

Define

2.29

 Defining

2.24

Activations Density 0.174%

occurrences of the word "defined" and related variations indicating the definition of terms or concepts

No Comments

No Known Activations