INDEX

Explanations

media outlets and news organizations

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

Tokens before and including "Life", "Post", or "Observer"

np_acts-logits-general · gemini-2.0-flash

news publications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Comprometido

-0.42

Tikang

-0.41

 Viena

-0.41

 GoogleFonts

-0.39

これからの

-0.38

ไหน

-0.38

lihatan

-0.38

 EdgeInsets

-0.37

 égard

-0.36

("}\

-0.36

POSITIVE LOGITS

UPI

0.63

tvguidetime

0.59



0.56

ViewFeatures

0.55

ANSA

0.53

 Reuters

0.51

putan

0.51

Referencer

0.49

printStackTrace

0.47

 Sputnik

0.45

Activations Density 0.267%

media outlets and news organizations

Tokens before and including "Life", "Post", or "Observer"

news publications

No Comments

No Known Activations