INDEX

Explanations

exclamation marks and expressions of excitement or emphasis

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

Exclamations

np_acts-logits-general · gemini-2.0-flash

end of emphatic clauses

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

ede

-0.86

gdx

-0.82

 Rump

-0.79

ation

-0.79

iNdEx

-0.79

[`

-0.72

 Wetter

-0.71

 Rés

-0.71

aure

-0.70

}`).

-0.69

POSITIVE LOGITS

?!?

1.42

?!?!

1.25

!!!!!!!

1.09

%!

1.07

!!!!!!

1.07

!!!!!!!!!!

1.03

~!

0.96

0.95

!!!!!!!!

0.94

Activations Density 0.076%

exclamation marks and expressions of excitement or emphasis

Exclamations

end of emphatic clauses

No Comments

No Known Activations