INDEX

Explanations

references to specific types of food and cooking techniques

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

glades

-0.53

alanta

-0.49

mphony

-0.49

族館

-0.49

EndTag

-0.46

Personendaten

-0.46

 departments

-0.45

ثيق

-0.44

 gynnwys

-0.44

 serviceName

-0.44

POSITIVE LOGITS

 bulat

0.67

PyExc

0.64

一个个

0.63

 تضيفلها

0.62

 minted

0.60

 themselves

0.56

 AssemblyCulture

0.56

참고

0.56

 shaped

0.56

 CGSize

0.55

Activations Density 0.873%

references to specific types of food and cooking techniques

No Comments

No Known Activations