INDEX

Explanations

programming structures and definitions related to procedures and classes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 giapp

-0.69

 avoient

-0.65

 mData

-0.64

 étoit

-0.63

 auroit

-0.62

 mourut

-0.59

 mList

-0.56

 rowCount

-0.56

agaimana

-0.55

BindingSource

-0.54

POSITIVE LOGITS

 change

0.94

 reset

0.85

get

0.85

 update

0.82

 take

0.80

 increase

0.80

re

0.78

 create

0.76

 move

0.75

 send

0.74

Activations Density 0.497%

programming structures and definitions related to procedures and classes

No Comments

No Known Activations