INDEX

Explanations

references to items and actions related to personal belongings and gatherings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 continúas

-0.68

ArrowToggle

-0.62

ParallelGroup

-0.61

ataires

-0.53

 PyLong

-0.53

 незавершена

-0.51

 mobiliario

-0.51

 leveren

-0.51

 masts

-0.50

PyTuple

-0.49

POSITIVE LOGITS

ScopeManager

0.78

 laptop

0.72

 notebook

0.72

 iPod

0.69

 portable

0.67

 iPad

0.67

 copy

0.64

 book

0.64

 Bible

0.63

 magnifying

0.62

Activations Density 0.309%

references to items and actions related to personal belongings and gatherings

No Comments

No Known Activations