INDEX

Explanations

formatting characters or structural elements in documents

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

Code snippets with hexadecimal values

np_acts-logits-general · gemini-2.0-flash

cross validation, interfaces, programming, question

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ఔ

-0.46

 NSCoder

-0.44

PageModule

-0.43

@[+][

-0.42

Roy

-0.41

Portail

-0.41

Datuak

-0.41

WireFormat

-0.41

ChildIndex

-0.40

 MediatR

-0.40

POSITIVE LOGITS

 propOrder

0.81

tagext

0.78

 ModelExpression

0.76

 Theſe

0.74

 reaſon

0.71

 myſelf

0.66

EndContext

0.65

клопе

0.65

 nakalista

0.65

 optique

0.62

Activations Density 0.062%

formatting characters or structural elements in documents

Code snippets with hexadecimal values

cross validation, interfaces, programming, question

No Comments

No Known Activations