INDEX

Explanations

professional titles and roles

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

Occupations or professions

np_acts-logits-general · gemini-2.0-flash

professions and job titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

Personendaten

-0.77

+#+#

-0.72

 Administrativna

-0.70

 '\\;'

-0.66

MigrationBuilder

-0.63

HandlerContext

-0.62

AddTagHelper

-0.60

Gambas

-0.59

kháu

-0.59

듬

-0.59

POSITIVE LOGITS

 extraordinaire

1.06

 specializing

1.01

 specialising

0.93

who

0.85

 turned

0.83

0.80

 manqué

0.75

兼

0.72

 AssemblyTitle

0.67

 working

0.65

Activations Density 0.180%

professional titles and roles

Occupations or professions

professions and job titles

No Comments

No Known Activations