INDEX

Explanations

personal invitations or requests for engagement.

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

contact information and invitations to events.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

phrases expressing invitation or welcoming participation, particularly using variations of "feel free to" or "you are welcome to".

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ویکی‌پدی

-0.70

 ComVisible

-0.55

IUrlHelper

-0.55

зулта

-0.55

 dAtA

-0.52

 jScrollPane

-0.51

niająca

-0.49

السكان

-0.49

łąd

-0.48

 ProtoMessage

-0.48

POSITIVE LOGITS

 welcome

1.78

welcome

1.43

 WELCOME

1.38

 Welcome

1.35

Welcome

1.21

 welcomed

1.15

 bienven

1.13

WELCOME

1.08

 welcomes

1.03

 bienvenue

0.93

Activations Density 0.115%

personal invitations or requests for engagement.

contact information and invitations to events.

phrases expressing invitation or welcoming participation, particularly using variations of "feel free to" or "you are welcome to".

No Comments

No Known Activations