INDEX

Explanations

terms associated with boundaries and transitions in narratives or processes

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

منابع

-0.45

 votos

-0.45

 لكرة

-0.44

Axios

-0.42

idov

-0.41

шенные

-0.41

ppon

-0.40

 Mull

-0.40

ForRow

-0.40

 تلاش

-0.39

POSITIVE LOGITS

DockStyle

0.83

 defaultstate

0.82

 BoxFit

0.70

ьаж

0.70

Parcelize

0.69

:✨

0.69

providedIn

0.67

UnusedPrivate

0.66

complexContent

0.64

脚注の使い方

0.62

Activations Density 0.711%

terms associated with boundaries and transitions in narratives or processes

No Comments

No Known Activations