INDEX

Explanations

references to something that is hot or temperature-related

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

脚注の使い方

-0.90

eraard

-0.86

theless

-0.86

quelize

-0.85

]").

-0.84

CloseOperation

-0.84

 Enix

-0.84

 JpaRepository

-0.83

Manga

-0.82

iastes

-0.81

POSITIVE LOGITS

hot

2.41

Hot

2.34

HOT

2.30

Hot

2.26

hot

2.21

HOT

2.14

 hotter

1.56

 hottest

1.55

ホット

1.34

 hotspot

1.18

Activations Density 0.033%

references to something that is hot or temperature-related

No Comments

No Known Activations