INDEX

Explanations

terms indicating invitations and organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

UserScript

-0.47

PostExecute

-0.43

 bezig

-0.40

phazard

-0.35

MessageTagHelper

-0.35

选手

-0.35

锈钢

-0.35

vège

-0.33

MigrationBuilder

-0.33

Aholisi

-0.33

POSITIVE LOGITS

 invitation

2.91

 invite

2.81

 invitations

2.63

 invites

2.55

 invited

2.53

 Invite

2.48

invitation

2.44

invite

2.42

 Invitation

2.42

INV

2.38

Activations Density 0.413%

terms indicating invitations and organization

No Comments

No Known Activations