INDEX

Explanations

elements related to location and dining experiences

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

enumi

-0.50

 Administrativna

-0.49

 déb

-0.48

">{

-0.47

ligent

-0.45

сну

-0.44

 kitchens

-0.44

 Juga

-0.44

zod

-0.43

///<

-0.43

POSITIVE LOGITS

 myſelf

0.79

 booked

0.74

 berdua

0.73

 chofe

0.70

Booked

0.67

 ourselves

0.64

ArrowToggle

0.63

 Monfieur

0.60

 spontan

0.59

 expecting

0.58

Activations Density 0.066%

elements related to location and dining experiences

No Comments

No Known Activations