INDEX

Explanations

keywords related to significance or categorization of subjects

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

ningens

-0.55

-0.54

mbalikan

-0.50

 Ombudsman

-0.49

 ModelExpression

-0.49

 Grüßen

-0.49

RunWith

-0.48

hnia

-0.47

 than

-0.47

SPATH

-0.47

POSITIVE LOGITS

 itſelf

0.81

tagHelperRunner

0.77

 myſelf

0.77

 Chriſt

0.76

 Theſe

0.73

 Monfieur

0.73

 Jefus

0.72

зулта

0.70

 himſelf

0.68

🏻‍♀️

0.67

Activations Density 0.291%

keywords related to significance or categorization of subjects

No Comments

No Known Activations