INDEX

Explanations

references to dishes or food presentations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abestanden

-0.80

دانشنامهٔ

-0.72

IntoConstraints

-0.67

ReusableCell

-0.64

ChromeDriver

-0.64

Atsauces

-0.58

COUVER

-0.55

WaitGroup

-0.54

 ligiloj

-0.54

unistd

-0.53

POSITIVE LOGITS

 issuance

0.71

 granting

0.71

 similarity

0.66

 grants

0.63

Iss

0.62

Iss

0.61

 issuing

0.60

ειτουργ

0.60

 granted

0.59

dish

0.58

Activations Density 0.124%

references to dishes or food presentations

No Comments

No Known Activations