INDEX

Explanations

indications of user interactions and responses in a digital comment section

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

}));

-0.54

MENAFN

-0.54

})));

-0.51

})).

-0.51

المناصب

-0.50

EndInit

-0.48

arrings

-0.47

 PrintWriter

-0.46

 Landes

-0.45

IBOutlet

-0.45

POSITIVE LOGITS

 gynhyrchwyd

0.58

 suivantes

0.56

 izvē

0.55

ArgsConstructor

0.55

 gustaMe

0.54



0.54

 Majesté

0.54

 laikā

0.53

PreferredItem

0.51

 MacGregor

0.50

Activations Density 0.077%

indications of user interactions and responses in a digital comment section

No Comments

No Known Activations