INDEX

Explanations

sentiments or assertions of superiority and self-importance among individuals

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

boasting or self-esteem

np_acts-logits-general · gemini-2.0-flash

inflated self-image

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

 contextLoads

-0.71

FormTagHelper

-0.65

ikum

-0.62

 transfieras

-0.61

MigrationBuilder

-0.54

thulhu

-0.54

("")]

-0.52

 оригіналу

-0.50

]=>

-0.49

 fidélité

-0.48

POSITIVE LOGITS

 pride

2.46

 proud

2.28

proud

2.13

 proudly

2.02

pride

2.00

Proud

1.98

 bragging

1.97

 Proud

1.95

 orgullo

1.91

 brag

1.90

Activations Density 0.351%

sentiments or assertions of superiority and self-importance among individuals

boasting or self-esteem

inflated self-image

No Comments

No Known Activations