INDEX

Explanations

references to "planes" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

paravant

-0.71

 sumpay

-0.69

NameInMap

-0.67

 betweenstory

-0.67

expliquer

-0.66

 Réponses

-0.66

 verrez

-0.64

 richi

-0.63

 recensement

-0.63

EDEFAULT

-0.62

POSITIVE LOGITS

 plane

1.86

 planes

1.80

 Plane

1.75

Plane

1.74

 PLANE

1.70

plane

1.68

 airplane

1.65

planes

1.59

PLANE

1.59

 Planes

1.51

Activations Density 0.070%

references to "planes" in various contexts

No Comments

No Known Activations