INDEX

Explanations

expressions related to invitations and the act of inviting

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Nadu

-0.66

 vulgaires

-0.64

RTLR

-0.64

endregion

-0.60

 γρα

-0.60

KEM

-0.59

يكب

-0.59

nasel

-0.58

тература

-0.58

SPR

-0.57

POSITIVE LOGITS

 invitation

1.20

 invitations

1.16

 invites

1.16

 invite

1.10

invitation

1.01

 Invite

0.97

 inviting

0.95

Invitation

0.95

 Invitation

0.94

 invited

0.91

Activations Density 0.073%

expressions related to invitations and the act of inviting

No Comments

No Known Activations