INDEX

Explanations

references to individuals or people in a general sense

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

TagHelpers

-0.86

Datuak

-0.73

anmoins

-0.68

かせて

-0.66

]=>

-0.65

 Spire

-0.64

matum

-0.63

 Epid

-0.62

UnusedPrivate

-0.62

 ویکی‌آمباردا

-0.60

POSITIVE LOGITS

Someone

2.23

 someone

2.16

someone

2.12

 Someone

2.11

Somebody

2.07

 somebody

1.99

 Somebody

1.98

 SOMEONE

1.90

somebody

1.80

 alguien

1.60

Activations Density 0.057%

references to individuals or people in a general sense

No Comments

No Known Activations