INDEX

Explanations

words or phrases related to actions, particularly in contexts involving stealth or escape

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

itulo

-0.52

dates

-0.51

uinal

-0.51

 systematic

-0.51

ographs

-0.50

atified

-0.48

 occupational

-0.48

 district

-0.48

Schedule

-0.47

chased

-0.47

POSITIVE LOGITS

 ModelExpression

0.83

 مرئيه

0.68

 विश्वसनीयता

0.66

mapStateToProps

0.65

__*/

0.63

']));

0.63

\}\\

0.62

RTLD

0.62

tagext

0.61

})->

0.61

Activations Density 0.616%

words or phrases related to actions, particularly in contexts involving stealth or escape

No Comments

No Known Activations