INDEX

Explanations

terms related to clarity and transparency in communication

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

"clear" followed by a variety of words

np_acts-logits-general · gemini-2.0-flash

clear and convincing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

OGND

-0.94

yntaxException

-0.92

DrawerToggle

-0.76

таратура

-0.75

FTFY

-0.74

RegistryLite

-0.72

Bibliograf

-0.72

Tikang

-0.70

#+#

-0.69

RequiresApi

-0.69

POSITIVE LOGITS

 clear

1.33

 Clear

1.30

 CLEAR

1.28

Clear

1.27

clear

1.14

 clears

1.13

 Clears

1.12

CLEAR

1.11

cut

0.96

cut

0.92

Activations Density 0.134%

terms related to clarity and transparency in communication

"clear" followed by a variety of words

clear and convincing

No Comments

No Known Activations