INDEX

Explanations

the use of contrasting conjunctions and qualifiers in discourse

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

*/}

-0.56

])));

-0.55

ંગ

-0.54

 صوتيه

-0.54

}))

-0.53

 AQUI

-0.53

"}";

-0.52

iedy

-0.52

twimg

-0.51

ásban

-0.50

POSITIVE LOGITS

 AssemblyCulture

0.68

ChildScrollView

0.52

 there

0.52

这就是

0.51

Mission

0.51

Think

0.51

 Autorisations

0.51

it

0.50

 SwitchCompat

0.50

 consuming

0.50

Activations Density 0.177%

the use of contrasting conjunctions and qualifiers in discourse

No Comments

No Known Activations