INDEX

Explanations

instances of significant actions and events involving medical emergencies

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

sequence, time, or physical state

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

⤹

-0.54

出版年

-0.51

 שוליים

-0.51

 quæ

-0.48

Vidite

-0.47

randomUUID

-0.47

 astore

-0.47

näm

-0.46

۪

-0.45

ftagPool

-0.45

POSITIVE LOGITS

principalTable

0.53

GOTREF

0.51

VIAF

0.40

 विश्वसनीयता

0.39

 استنادى

0.36

 afterwards

0.35

 voer

0.35

 subsequently

0.35

FDRE

0.34

RefNanny

0.34

Activations Density 0.036%

instances of significant actions and events involving medical emergencies

sequence, time, or physical state

No Comments

No Known Activations