INDEX

Explanations

references to domains or domain concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Clegg

-0.73

 McClure

-0.68

 devons

-0.66

 engagé

-0.62

หมือน

-0.62

 scio

-0.61

appoint

-0.60

 καλ

-0.60

~•

-0.60

 Nunn

-0.60

POSITIVE LOGITS

 domain

2.70

 Domain

2.57

 domains

2.47

domain

2.40

Domain

2.37

 Domains

2.24

 DOMAIN

2.22

DOMAIN

2.14

domains

2.06

Domains

2.04

Activations Density 0.044%

references to domains or domain concepts

No Comments

No Known Activations