INDEX

Explanations

terms related to medical conditions or health-related topics

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

"bed" or being in "bed"

np_acts-logits-general · gemini-2.0-flash

bed, beds, mattresses, mattress

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/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.24.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

enderror

-0.58

aarrggbb

-0.58

anterie

-0.57

endphp

-0.57

 Lleva

-0.56

 ब्रेकडाउन

-0.55

 Sociales

-0.55

WEBPACK

-0.55

LEncoder

-0.54

hlands

-0.53

POSITIVE LOGITS

bed

1.36

 beds

1.01

 bunk

0.93

bed

0.89

Bed

0.85

 queen

0.85

 mattress

0.83

 single

0.83

 cama

0.83

Bed

0.82

Activations Density 0.109%

terms related to medical conditions or health-related topics

"bed" or being in "bed"

bed, beds, mattresses, mattress

No Comments

No Known Activations