INDEX

Explanations

instructional verbs related to cooking and data manipulation processes

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

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

 ويكيميديا

-0.75

 للمعارف

-0.72

didSet

-0.69

 مرئيه

-0.67

 disambiguazione

-0.64

XmlAccessType

-0.62

Демографія

-0.61

Verweise

-0.58

 Italijanski

-0.57

brainly

-0.56

POSITIVE LOGITS

 them

1.12

it

0.93

 your

0.74

 everything

0.71

 chúng

0.67

 totul

0.63

 őket

0.63

 each

0.62

 ciasc

0.59

them

0.58

Activations Density 0.607%

instructional verbs related to cooking and data manipulation processes

No Comments

No Known Activations