INDEX

Explanations

structured data or instances that involve lists or sequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ngdoc

-0.63

…

-0.59

…

-0.58

ProcessEvent

-0.56

 <>",

-0.56

Географи

-0.54

NSNotification

-0.54

 […]

-0.52

="#">

-0.52

Посилання

-0.51

POSITIVE LOGITS

:✨

0.68

 cited

0.65

 дописавши

0.60

 footnote

0.58

EndInit

0.54

 Forth

0.54

expandindo

0.52

bibitem

0.52

 utafitiHapana

0.52

 citation

0.51

Activations Density 0.140%

structured data or instances that involve lists or sequences

No Comments

No Known Activations