INDEX

Explanations

references to dining experiences and restaurant settings

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

nearby restaurant outside locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 ویکی‌پدیا

-0.50

ListItemIcon

-0.50

ArrowToggle

-0.49

XmlAccessType

-0.49

 signifikan

-0.44

astanza

-0.43

 regalías

-0.42

 leveren

-0.41

Handlung

-0.40

fjspx

-0.40

POSITIVE LOGITS

 beach

0.44

 Meksiku

0.42

 seaside

0.42

Activated

0.41

Words

0.41

ſelves

0.41

Życiorys

0.41

chromedriver

0.40

Hun

0.40

 myſelf

0.40

Activations Density 0.028%

references to dining experiences and restaurant settings

nearby restaurant outside locations

No Comments

No Known Activations