INDEX

Explanations

instance of the word "Read" and its variations, indicating an emphasis on articles or sections to be read

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

setVerticalGroup

-1.04

 Мексичка

-0.93

GEBURTSDATUM

-0.90

ConstraintMaker

-0.84

évaluateur

-0.83

 mergeFrom

-0.81

StructEnd

-0.81

 utafitiHapana

-0.78

 незавершена

-0.77

IsMutable

-0.77

POSITIVE LOGITS

Read

2.49

 Read

1.60

Leggi

1.12

Continue

1.11

Läs

0.97

Weiterlesen

0.78

Lire

0.76

Показать

0.76

Читайте

0.74

Læs

0.73

Activations Density 0.162%

instance of the word "Read" and its variations, indicating an emphasis on articles or sections to be read

No Comments

No Known Activations