INDEX

Explanations

comparisons involving size, quantity, or measurement

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

 myſelf

-0.71

Efq

-0.69

 Jefus

-0.67

 Majefty

-0.67

 تانيه

-0.67

IntoConstraints

-0.66

}}/>

-0.64

 uſed

-0.64

 Chrift

-0.64

 Chriſt

-0.62

POSITIVE LOGITS

ground

0.62

saraba

0.58

่

0.57

getOut

0.54

 normal

0.52

わい

0.50

enumi

0.50

 normale

0.50

dec

0.49

md

0.49

Activations Density 0.504%

comparisons involving size, quantity, or measurement

No Comments

No Known Activations