INDEX

Explanations

instances of the prefix "un-" indicating negation or absence

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AndEndTag

-0.74

ScopeManager

-0.73

MemoryWarning

-0.72

 Gegenteil

-0.66

ckså

-0.65

QMetaType

-0.63

 HasFactory

-0.63

 AssemblyCompany

-0.61

цездатний

-0.60



-0.60

POSITIVE LOGITS

un

1.70

Un

1.57

Un

1.53

un

1.29

UN

1.16

UN

0.96

Una

0.88

unf

0.85

Uns

0.83

Uns

0.82

Activations Density 0.121%

instances of the prefix "un-" indicating negation or absence

No Comments

No Known Activations