INDEX

Explanations

word tokens related to invitations or extending invites

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ksessa

-0.56

Inoltre

-0.54

ksesta

-0.50

Fase

-0.50

 misure

-0.49

 guma

-0.49

Semif

-0.48

HasMaxLength

-0.48

 teras

-0.48

 ricerche

-0.48

POSITIVE LOGITS

 Invited

1.27

 Invite

1.24

 invite

1.23

 depic

1.23

 invitation

1.21

 Invitation

1.20

 reluct

1.20

 invitations

1.19

 invited

1.14

 invites

1.13

Activations Density 0.072%

word tokens related to invitations or extending invites

No Comments

No Known Activations