INDEX

Explanations

statements that express apologies or address misunderstandings

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

Expressions of regret or apology

np_acts-logits-general · gemini-2.0-flash

apologies and mistakes

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

 rangs

-0.39

ellt

-0.38

 precies

-0.37

afat

-0.36

aarrggbb

-0.36

 mengan

-0.36

眉头

-0.36

 strani

-0.36

or

-0.35

ActiveRecord

-0.34

POSITIVE LOGITS

 apologies

1.23

 apologize

1.23

 Oops

1.18

 apologized

1.17

 apology

1.11

 apologise

1.10

 apologizing

1.10

 oops

1.09

Apologies

1.08

 apologised

1.07

Activations Density 0.214%

statements that express apologies or address misunderstandings

Expressions of regret or apology

apologies and mistakes

No Comments

No Known Activations