INDEX

Explanations

references to user data management and privacy policies

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

followed by instructions or conditions

np_acts-logits-general · gemini-2.0-flash

customizable options

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

enumi

-0.63

moveToNext

-0.56

 CURIAM

-0.55

reibung

-0.50

PageIndex

-0.49

 مُعرِّف

-0.49

 Knud

-0.49

 <<<<<<<<<<<<<<

-0.48

ConnectionState

-0.47

хь

-0.47

POSITIVE LOGITS

 customizable

0.97

 customization

0.95

 adjustable

0.85

 Customizable

0.82

 customize

0.82

 Customization

0.81

 configurable

0.81

 customizing

0.81

 réglable

0.80

 Option

0.79

Activations Density 0.494%

references to user data management and privacy policies

followed by instructions or conditions

customizable options

No Comments

No Known Activations