INDEX

Explanations

comparative language indicating deficiency or reduced quantities

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

"Less" followed by comparative words

np_acts-logits-general · gemini-2.0-flash

less than a quantity or degree

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Kirkwood

-0.75

 ['./

-0.67

 οποία

-0.67

LEGGI

-0.65

YECTO

-0.64

izare

-0.63

ratulations

-0.62

mountable

-0.62

rabbitmq

-0.62

orologio

-0.61

POSITIVE LOGITS

 LESS

1.15

 Less

1.03

 less

1.02

Less

0.94

 than

0.93

 Lessing

0.86

less

0.86

LESS

0.81

 menos

0.74

 THAN

0.73

Activations Density 0.087%

comparative language indicating deficiency or reduced quantities

"Less" followed by comparative words

less than a quantity or degree

No Comments

No Known Activations