INDEX

Explanations

programming-related terms and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Anhalt

-0.51

engeance

-0.50

rinth

-0.50

elry

-0.49

renched

-0.49

 Incorporated

-0.49

 CHINA

-0.49

downe

-0.48

 CLOS

-0.48

 China

-0.47

POSITIVE LOGITS

 /\.(

0.75

IntoConstraints

0.71

multirow

0.68

webElementXpaths

0.68

 propOrder

0.67

NameInMap

0.66

UnknownFields

0.66

 disambiguazione

0.61

IsContent

0.59

XMLSchema

0.58

Activations Density 0.200%

programming-related terms and functions

No Comments

No Known Activations