INDEX

Explanations

occurrences of the word "wear" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

(',')

-0.82

 Cousins

-0.74

 Pritchard

-0.72

loß

-0.68

 bụng

-0.68

 McGee

-0.67

itol

-0.66

来不及

-0.66

 decisivo

-0.66

Allister

-0.66

POSITIVE LOGITS

 Wear

1.41

 wear

1.37

 worn

1.31

Wear

1.31

 wears

1.24

wear

1.21

 WEAR

1.20

 Worn

1.19

 wearer

1.14

 Wearing

1.10

Activations Density 0.030%

occurrences of the word "wear" and its variations

No Comments

No Known Activations