INDEX

Explanations

terms related to specific cuisines and healthcare topics

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

acupuncture, Medicare, Arthrex

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

Negative Logits

 Osorio

-0.46

-0.45

<b>

-0.40

 Mejía

-0.38

sav

-0.37

KNOWN

-0.37

Slf

-0.37

 Herrschaft

-0.37

-0.36

bujete

-0.36

POSITIVE LOGITS

 acupuncture

2.42

upuncture

2.25

 Acupuncture

2.16

upun

1.06

鍼

1.04

untura

0.85

 chiropractic

0.81

 YOGA

0.76

 physiotherapy

0.75

 yoga

0.73

Activations Density 0.002%

terms related to specific cuisines and healthcare topics

acupuncture, Medicare, Arthrex

No Known Activations