INDEX

Explanations

references to legal documents and official statements

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

official statements

np_acts-logits-general · gemini-2.0-flash

reporting speech and official statements

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

 ब्रेकडाउन

-0.70

Trayectoria

-0.66

Билгалдахарш

-0.63

 externi

-0.61

новништво

-0.58

abestanden

-0.58

Personensuche

-0.58

MLLoader

-0.58

initComponents

-0.57

UserScript

-0.57

POSITIVE LOGITS

DBG

0.33

adə

0.32

sen

0.32

 said

0.30

 sign

0.30

 indicate

0.30

 memo

0.30

anovic

0.29

 indicated

0.29

 indic

0.29

Activations Density 0.390%

references to legal documents and official statements

official statements

reporting speech and official statements

No Comments

No Known Activations