INDEX

Explanations

technical terms related to software code and data types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Normdatei

-0.55

 invokingState

-0.52

Kariera

-0.51

]}

-0.48

OGND

-0.48

포

-0.46

//};

-0.45

"]}

-0.45

참고

-0.45

}`}

-0.44

POSITIVE LOGITS

 كومونز

0.76

 ModelExpression

0.73

 <>",

0.71

 AssemblyProduct

0.67

 بيها

0.59

HtmlAttribute

0.58

didSet

0.57

Selectors

0.57

UIControlState

0.56

 Selector

0.55

Activations Density 0.188%

technical terms related to software code and data types

No Comments

No Known Activations