INDEX

Explanations

statements regarding authorship and potential conflicts of interest in research articles

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

conceived and designed

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

nehmer

-0.31

din

-0.30

inc

-0.29

Abp

-0.29

yyr

-0.29

 softness

-0.28

 dije

-0.28

till

-0.27

ern

-0.27

FB

-0.26

POSITIVE LOGITS

 NSCoder

0.69

oredCriteria

0.64

 дописавши

0.63

contentLoaded

0.62

 Савезне

0.59

Diwedd

0.58

MemoryWarning

0.56

SpringBootTest

0.54

 للمعارف

0.53

ConstraintMaker

0.53

Activations Density 1.014%

statements regarding authorship and potential conflicts of interest in research articles

conceived and designed

No Comments

No Known Activations