INDEX

Explanations

phrases related to actions and activities, especially involving travel and work

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

work and travel

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

Erreferentziak

-0.63



-0.59

verwijspagina

-0.50

dillos

-0.49

Біографія

-0.49

 Infórmanos

-0.48

 Numerade

-0.48

 betweenstory

-0.47

 nonUne

-0.45

 propOrder

-0.44

POSITIVE LOGITS

 visit

0.64

 visiting

0.63

 visits

0.55

Visiting

0.52

 trip

0.51

visiting

0.50

 visita

0.49

 abroad

0.49

 besök

0.49

visit

0.48

Activations Density 0.134%

phrases related to actions and activities, especially involving travel and work

work and travel

No Comments

No Known Activations