INDEX

Explanations

occurrences of specific events and their frequency in a legal or conversational context

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

frequency or repetition

np_acts-logits-general · gemini-2.0-flash

multiple occurrences

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

saraba

-0.66

contentLoaded

-0.63

IContainer

-0.61

قایناق‌لار

-0.57

bootstrapcdn

-0.56

Vidite

-0.55

 تضيفلها

-0.54

 '\\;'

-0.54

exitRule

-0.53

apeake

-0.51

POSITIVE LOGITS

 repeatedly

0.48

 frequent

0.41

几次

0.41

 fotográfico

0.38

 throughout

0.38

 times

0.37

 fréquent

0.36

 frequently

0.36

repeated

0.35

 repeated

0.35

Activations Density 0.858%

occurrences of specific events and their frequency in a legal or conversational context

frequency or repetition

multiple occurrences

No Comments

No Known Activations