INDEX

Explanations

actions related to cleaning or wiping

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

cleaning or wiping

np_acts-logits-general · gemini-2.0-flash

cleaning and clearing

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 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

+:+

-0.53

waitKey

-0.52

 Annal

-0.52

 Delano

-0.49

optarg

-0.49

 AssemblyProduct

-0.49

 fermés

-0.49

lå

-0.48

OGND

-0.47

󠁿

-0.47

POSITIVE LOGITS

Clearing

0.94

 clearing

0.90

 cleared

0.82

 Clearing

0.82

 clears

0.82

clearing

0.81

 Clears

0.80

cleared

0.79

)";

0.77

Cleared

0.77

Activations Density 0.124%

actions related to cleaning or wiping

cleaning or wiping

cleaning and clearing

No Comments

No Known Activations