INDEX

Explanations

references to a portfolio or collection of items or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

RefNanny

-0.60

 Exacts

-0.57

 متعلقه

-0.56

 Injectable

-0.54

findpost

-0.53

 shape

-0.52

 AssemblyCulture

-0.51

тек

-0.50

出版年

-0.50

Gambas

-0.48

POSITIVE LOGITS

 portfolio

0.89

 boundary

0.81

 powerful

0.81

 Boundary

0.79

Boundary

0.78

boundary

0.78

 playlist

0.77

 Portfolio

0.77

AnchorStyles

0.77

 greateſt

0.76

Activations Density 0.055%

references to a portfolio or collection of items or information

No Comments

No Known Activations