INDEX

Explanations

medical terminology related to serious adverse events and their management

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

Actions requiring notification or reporting

np_acts-logits-general · gemini-2.0-flash

report, notify, contact, inform, disclose

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

 snippetHide

-1.02

RenderAtEndOf

-0.98

Personensuche

-0.97

 cherchés

-0.97

 doInBackground

-0.87

awtextra

-0.84

 autorytatywna

-0.84

WireFormatLite

-0.82

SourceChecksum

-0.82

LoadScene

-0.77

POSITIVE LOGITS

 reporting

0.68

Notify

0.65

 notify

0.65

 alerted

0.64

 notifying

0.64

 notified

0.64

 immediately

0.61

 alert

0.60

 report

0.60

 reported

0.60

Activations Density 0.229%

medical terminology related to serious adverse events and their management

Actions requiring notification or reporting

report, notify, contact, inform, disclose

No Comments

No Known Activations