INDEX

Explanations

the use of qualifying adverbs and phrases

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

 समीक्षाएं

-0.90

évaluateur

-0.85

 autorytatywna

-0.80

 SwitchCompat

-0.79

__':

-0.78

 kasarigan

-0.76

extAlignment

-0.75

 kaarangay

-0.75

 BoxFit

-0.74

webElementXpaths

-0.74

POSITIVE LOGITS

 actually

0.84

 egentlig

0.70

actually

0.67

 really

0.66

Actually

0.64

 eigentlich

0.62

 faktisk

0.62

 egentligen

0.62

 Actually

0.59

 eigenlijk

0.59

Activations Density 0.265%

the use of qualifying adverbs and phrases

No Comments

No Known Activations