INDEX

Explanations

expressions related to updates or edits in written discussions

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

достатки

-0.61

abstractmethod

-0.59

//

-0.54

 Мексичка

-0.52

ISODE

-0.50

لهم

-0.47

 scene

-0.47

៹

-0.47

 }}">

-0.45

us

-0.45

POSITIVE LOGITS

存于互联网档案馆

0.70

 añad

0.69

 corrig

0.68

ValueStyle

0.66

 добав

0.64

Aktualisiert

0.63

[--

0.63

 clarification

0.63

IndentedString

0.62

 acresc

0.61

Activations Density 0.160%

expressions related to updates or edits in written discussions

No Comments

No Known Activations