INDEX

Explanations

occurrences of the word "clean" 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 @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

-1.03

 AssemblyCulture

-0.99

المناصب

-0.98

antMatchers

-0.91

 Lottie

-0.87

 immobilier

-0.86

دواج

-0.86

 CreateTagHelper

-0.86

zczegól

-0.86

__':

-0.85

POSITIVE LOGITS

 Clean

1.36

 CLEAN

1.31

 cleans

1.22

Clean

1.21

CLEAN

1.20

 clean

1.15

 cleaner

1.12

clean

1.09

cleaner

1.09

 cleaning

1.03

Activations Density 0.097%

occurrences of the word "clean" and its variations

No Comments

No Known Activations