INDEX

Explanations

references to studies and research findings, particularly related to health or psychological conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Administrativna

-0.56

 متعلقه

-0.47

CreateModel

-0.46

☆☆☆☆

-0.46

⇑

-0.46

.*")]

-0.46

 &___

-0.45

rungsseite

-0.45

 beginnetje

-0.44

Tey

-0.44

POSITIVE LOGITS

 found

3.24

found

2.75

 Found

2.64

Found

2.40

 FOUND

2.34

FOUND

2.03

 discovered

1.95

 ditemukan

1.84

 gefunden

1.84

 trouvé

1.76

Activations Density 0.732%

references to studies and research findings, particularly related to health or psychological conditions

No Comments

No Known Activations