INDEX

Explanations

terms related to tumors and medical conditions involving diagnostic imaging

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

or abbreviations followed by numbers

np_acts-logits-general · gemini-2.0-flash

foreign words, language identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 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

setVerticalGroup

-0.65

InputBorder

-0.63

addPreferredGap

-0.62

AnchorStyles

-0.59

AnchorTagHelper

-0.58

addContainerGap

-0.56

iastes

-0.56

دانشنامهٔ

-0.55

 الحره

-0.54

 StringTokenizer

-0.54

POSITIVE LOGITS

 himo

0.37

 Schließlich

0.36

moldura

0.36

Tos

0.35

 ciascuno

0.34

 confira

0.34

Nombre

0.34

 nämlich

0.34

 himſelf

0.34

lua

0.34

Activations Density 1.750%

terms related to tumors and medical conditions involving diagnostic imaging

or abbreviations followed by numbers

foreign words, language identifiers

No Comments

No Known Activations