INDEX

Explanations

code snippets related to NumPy and array manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 تضيفلها

-0.69

findOrFail

-0.60

EnableWeb

-0.60

 Dresden

-0.58

NDL

-0.58

Kund

-0.56

odeon

-0.56

abilirsiniz

-0.55

Trả

-0.55

DrawerToggle

-0.55

POSITIVE LOGITS

np

1.13

np

0.94

 numpy

0.85

asarray

0.80

NPs

0.77

umpy

0.74

 ModelExpression

0.71

NPY

0.71

NP

0.70

ostante

0.70

Activations Density 0.038%

code snippets related to NumPy and array manipulation

No Comments

No Known Activations