INDEX

Explanations

mentions of the word "medical."

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

"Medical" followed by related terms

np_acts-logits-general · gemini-2.0-flash

medical students, research, records, care

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

TypedDataSet

-0.87

IsContent

-0.81

 linkovi

-0.75

 مرئيه

-0.73

########.

-0.72

Diwedd

-0.69

,‎

-0.69

SequentialGroup

-0.68

Efq

-0.67

 saites

-0.66

POSITIVE LOGITS

TagMode

0.53

 medical

0.48

 device

0.46

Medical

0.44

вед

0.44

Ball

0.43

вер

0.42

กรรม

0.42

 Medical

0.42

 Google

0.41

Activations Density 0.129%

mentions of the word "medical."

"Medical" followed by related terms

medical students, research, records, care

No Comments

No Known Activations