INDEX

Explanations

phrases related to acting or performing, particularly in a theatrical or leadership context.

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

actions related to leadership and responsibility.

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

words related to acting or performance.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

The root word "act" and its variations

np_acts-logits-general · gemini-2.0-flash

acting as roles and actuation

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

 nahilalakip

-0.69

 sterili

-0.61

ViewFeatures

-0.58

ftagPool

-0.57

ReusableCell

-0.56

multer

-0.55

 rând

-0.54

 Marconi

-0.54

 sterilized

-0.54

 Psyche

-0.52

POSITIVE LOGITS

 acts

0.83

ACT

0.77

 Acts

0.76

act

0.71

acts

0.70

 acted

0.67

uate

0.67

uation

0.64

ACT

0.64

 acto

0.64

Activations Density 0.082%

phrases related to acting or performing, particularly in a theatrical or leadership context.

actions related to leadership and responsibility.

words related to acting or performance.

The root word "act" and its variations

acting as roles and actuation

No Comments

No Known Activations