INDEX

Explanations

negation terms and their contexts in discussions

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

expressions of negation and doubt

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

negation and lack of significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 disponibilités

-0.68

TagHelper

-0.64

HasAnnotation

-0.61

ỡng

-0.59

fjspx

-0.59

//

-0.56

 correctes

-0.55

 ErrIntOverflow

-0.55

hiasan

-0.54

POSITIVE LOGITS

ScopeManager

0.81

 insurmountable

0.69

 unduly

0.59

 unreasonable

0.58

BitmapFactory

0.55

 unusual

0.54

 JpaRepository

0.54

 naman

0.54

 dramatically

0.53

 major

0.53

Activations Density 0.211%

negation terms and their contexts in discussions

expressions of negation and doubt

negation and lack of significance

No Comments

No Known Activations