INDEX

Explanations

references to research, studies, and analyses related to scientific or legal contexts

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

medical diagnosis complications

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

enterOuterAlt

-0.46

OuterAlt

-0.40

 tetrachloride

-0.34

endmodule

-0.33

HasIndex

-0.33

oa̍t

-0.32

 Universidades

-0.31

 censiti

-0.31

 spent

-0.31

 Special

-0.31

POSITIVE LOGITS

IContainer

0.52

Identyfik

0.48

ftest

0.46

 intStringLen

0.45

 autorytatywna

0.44

 dopiero

0.44

PrototypeOf

0.42

 plutôt

0.42

Manbalar

0.42

 siebie

0.42

Activations Density 0.216%

references to research, studies, and analyses related to scientific or legal contexts

medical diagnosis complications

No Comments

No Known Activations