INDEX

Explanations

references to citations and published works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 disambiguazione

-0.83

 Roskov

-0.81

ArgsConstructor

-0.74

PreferredItem

-0.74

 NUKAT

-0.66

tvguidetime

-0.66

 للمعارف

-0.65

omeness

-0.65

tagHelperRunner

-0.64

 erlä

-0.64

POSITIVE LOGITS

]})

0.57

@}

0.51

wien

0.48

 almost

0.47

indelijk

0.45

])));

0.45

“

0.45

Etimología

0.45

>--}}

0.44

kiel

0.44

Activations Density 0.132%

references to citations and published works

No Comments

No Known Activations