INDEX

Explanations

references to biological classifications or variants

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

after capitalized abbreviations

np_acts-logits-general · gemini-2.0-flash

listing specific items to categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 pouvoirs

-0.95

 bénéfices

-0.88

 bienfaits

-0.87

 fidèles

-0.85

GEBURTSDATUM

-0.85

 vérit

-0.85

 enfans

-0.84

 lèvres

-0.84

 prêtres

-0.83

 autorités

-0.82

POSITIVE LOGITS

 respectively

1.70

respectively

1.50

 respectivamente

1.31

それぞれ

1.20

 alike

1.18

 respective

1.13

 jeweils

1.03

 respectivement

1.03

 both

0.99

分别

0.98

Activations Density 1.029%

references to biological classifications or variants

after capitalized abbreviations

listing specific items to categories

No Comments

No Known Activations