INDEX

Explanations

conjunctions and transitional phrases used in arguments or explanations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Wikispecies

-0.53

庁

-0.51

assung

-0.51

Xna

-0.50

 comis

-0.49

::_('

-0.48

 OFDb

-0.48

classnames

-0.48

GEBURTSDATUM

-0.47

quim

-0.47

POSITIVE LOGITS

FormTagHelper

0.65

/>";

0.61

vlád

0.58

BeginContext

0.57

subplot

0.56

Біографія

0.55

 NDEBUG

0.55

[]]

0.55

}';

0.55

Gön

0.54

Activations Density 0.081%

conjunctions and transitional phrases used in arguments or explanations

No Comments

No Known Activations