INDEX

Explanations

instances of the word "create" and its variations, indicating a focus on creation processes or functions

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

the word "create"

np_acts-logits-general · gemini-2.0-flash

creating objects or structures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

woof

-0.65

 CanadaChoose

-0.63

+#+

-0.62

antMatchers

-0.61

StatusBadRequest

-0.61

NegativeButton

-0.58

owohl

-0.57

 Moth

-0.56

}{*}{}

-0.56

 Lond

-0.56

POSITIVE LOGITS

 havoc

0.73

oredCriteria

0.70

/−

0.64

 literaria

0.64

Pautan

0.63

 sztu

0.62

 Lacy

0.62

ghton

0.59

 впечатление

0.58

anstalt

0.57

Activations Density 0.063%

instances of the word "create" and its variations, indicating a focus on creation processes or functions

the word "create"

creating objects or structures

No Comments

No Known Activations