INDEX

Explanations

references to code structure and data operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

:✨

-0.72

XtraReports

-0.60

findpost

-0.59

 EconPapers

-0.59

fjspx

-0.58

IntoConstraints

-0.57

Personendaten

-0.55

MessageOf

-0.55

)++;

-0.53

webElement

-0.52

POSITIVE LOGITS

 NDEBUG

0.70

 foncé

0.62

randomUUID

0.59

actéristique

0.57

ValueGeneration

0.54

requireNonNull

0.54

 useHistory

0.53

 useNavigate

0.52

 abstrait

0.52

 Longueur

0.51

Activations Density 0.200%

references to code structure and data operations

No Comments

No Known Activations