INDEX

Explanations

terms related to medical procedures and assessments

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

Something is/was/were/are included/involved

np_acts-logits-general · gemini-2.0-flash

included in something

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

brtc

-0.59

 createState

-0.56

istoitu

-0.55

MENAFN

-0.53

eeqa

-0.52

Uploaded

-0.52

öbb

-0.51

setupUi

-0.51

 PriorityQueue

-0.51

tehenden

-0.50

POSITIVE LOGITS

 included

2.41

 involved

2.15

included

2.00

 Included

1.86

 consisted

1.73

involved

1.72

Included

1.69

 INCLUDED

1.64

 Involved

1.63

 entailed

1.52

Activations Density 0.823%

terms related to medical procedures and assessments

Something is/was/were/are included/involved

included in something

No Comments

No Known Activations