INDEX

Explanations

expressions of positive sentiment or happiness

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

ArgsConstructor

-0.76

 Paglinawan

-0.75

INCT

-0.75

WebVitals

-0.70

 Hecht

-0.68

iformis

-0.67

AllAfrica

-0.67

DispatchToProps

-0.66

 disponibilités

-0.64

 ElementRef

-0.63

POSITIVE LOGITS

prob

1.06

 probable

0.99

 PROB

0.89

probable

0.86

 prob

0.83

 probab

0.83

 wahrscheinlich

0.80

Prob

0.78

 probably

0.77

 Probable

0.76

Activations Density 0.117%

expressions of positive sentiment or happiness

No Comments

No Known Activations