INDEX

Explanations

code syntax for namespaces and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

invokeLater

-0.94

StoryboardSegue

-0.91

 nakalista

-0.88

 <>",

-0.81

routeProvider

-0.81

featureID

-0.81

SequentialGroup

-0.74

 MenuView

-0.73

NamedQueries

-0.73

 BitmapFactory

-0.72

POSITIVE LOGITS

::

0.69

::

0.63

ద్య

0.61

Pyx

0.60

 مرئيه

0.58

__*/

0.57

rie

0.56

Gli

0.56

 iParam

0.53

niv

0.53

Activations Density 0.005%

code syntax for namespaces and function definitions

No Comments

No Known Activations