INDEX

Explanations

references to travel experiences, particularly on cruises

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

 kite

-0.52

 foramen

-0.51

ilon

-0.49

 Drone

-0.49

 configureStore

-0.47

 kites

-0.47

 Tetrahedron

-0.47

 SUDOC

-0.46

 thèse

-0.46

 фона

-0.45

POSITIVE LOGITS

 cruise

1.08

 Cruise

0.95

 ship

0.94

cruise

0.94

 cruises

0.85

ship

0.83

Cruise

0.82

 Carnival

0.77

oredCriteria

0.77

Cun

0.75

Activations Density 0.048%

references to travel experiences, particularly on cruises

No Comments

No Known Activations