INDEX

Explanations

terms related to testing and validation in programming

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

Code-related keywords and identifiers

np_acts-logits-general · gemini-2.0-flash

should followed by action or property

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/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.16.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

MetaObject

-0.51

 wherever

-0.50

 destinés

-0.49

 Wherever

-0.45

Wherever

-0.45

writeHead

-0.45

or

-0.44

<eos>

-0.44

DropTable

-0.44

hichever

-0.44

POSITIVE LOGITS

 يتيمه

0.83

 AssemblyCulture

0.78

AddTagHelper

0.76

TagHelper

0.71

 chi̍t

0.70

 myſelf

0.69

 الحره

0.68

 pinulongan

0.67

YMMV

0.64

rungsseite

0.64

Activations Density 0.350%

terms related to testing and validation in programming

Code-related keywords and identifiers

should followed by action or property

No Comments

No Known Activations