INDEX

Explanations

references to individuals or entities regarded as members of a group or organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

styleType

-0.76

neux

-0.55

bium

-0.50

ifrance

-0.50

äu

-0.50

✨:

-0.50

міністра

-0.49

Према

-0.48

 himo

-0.47

mators

-0.47

POSITIVE LOGITS

 member

2.56

 Member

2.46

Member

2.32

member

2.26

 MEMBER

2.19

MEMBER

1.88

 Mitglied

1.53

 miembro

1.32

 membro

1.28

 membre

1.21

Activations Density 0.106%

references to individuals or entities regarded as members of a group or organization

No Comments

No Known Activations