INDEX

Explanations

references to saints and holy items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 للمعارف

-0.90

 ivelany

-0.84

extAlignment

-0.67

الإنجليزية

-0.65

клопе

-0.65

脚注の使い方

-0.63

UnusedPrivate

-0.63

 demografica

-0.62

complexContent

-0.61

 esternos

-0.60

POSITIVE LOGITS

 saints

0.72

 saint

0.69

 martyr

0.62

 Saints

0.61

 martyrdom

0.60

 betweenstory

0.58

aints

0.57

Sain

0.55

 SAINT

0.55

 Sain

0.54

Activations Density 0.150%

references to saints and holy items

No Comments

No Known Activations