INDEX

Explanations

names, relationships, and titles of individuals and entities within the content

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

First-person statements about current situations

np_acts-logits-general · gemini-2.0-flash

who have

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 becomes

-0.65

Hentet

-0.63

becomes

-0.62

تقاوى

-0.59

tokio

-0.56

Przypisy

-0.56

stateProvider

-0.54

 /\.(

-0.53

urlpatterns

-0.52

 redux

-0.52

POSITIVE LOGITS

 regularly

1.17

 routinely

1.04

 recently

0.94

 frequently

0.89

 regularmente

0.87

 currently

0.86

 operates

0.84

recently

0.83

 operate

0.81

 Regularly

0.80

Activations Density 0.767%

names, relationships, and titles of individuals and entities within the content

First-person statements about current situations

who have

No Comments

No Known Activations